Update the vendored unicodecsv to fix None handling

The old version of unicodecsv incorrectly (according
https://docs.python.org/2/library/csv.html#csv.writer) encoding None
values as the string 'None', instead of the string '' as the python
documentation specifies.

The newest version of unicodecsv has fixed this.

Fixes #121

1 files changed, 143 insertions, 51 deletions

diff --git a/tablib/packages/unicodecsv/__init__.py b/tablib/packages/unicodecsv/__init__.py
index e640987..6a20118 100644
--- a/tablib/packages/unicodecsv/__init__.py
+++ b/tablib/packages/unicodecsv/__init__.py
@@ -1,22 +1,65 @@
 # -*- coding: utf-8 -*-
 import csv
-from csv import *
+try:
+    from itertools import izip
+except ImportError:
+    izip = zip
 
 #http://semver.org/
-VERSION = (0, 8, 0)
+VERSION = (0, 10, 1)
 __version__ = ".".join(map(str,VERSION))
 
-def _stringify(s, encoding):
-    if type(s)==unicode:
-        return s.encode(encoding)
+pass_throughs = [
+    'register_dialect',
+    'unregister_dialect',
+    'get_dialect',
+    'list_dialects',
+    'field_size_limit',
+    'Dialect',
+    'excel',
+    'excel_tab',
+    'Sniffer',
+    'QUOTE_ALL',
+    'QUOTE_MINIMAL',
+    'QUOTE_NONNUMERIC',
+    'QUOTE_NONE',
+    'Error'
+]
+__all__ = [
+    'reader',
+    'writer',
+    'DictReader',
+    'DictWriter',
+] + pass_throughs
+
+for prop in pass_throughs:
+    globals()[prop]=getattr(csv, prop)
+
+def _stringify(s, encoding, errors):
+    if s is None:
+        return ''
+    if isinstance(s, unicode):
+        return s.encode(encoding, errors)
     elif isinstance(s, (int , float)):
         pass #let csv.QUOTE_NONNUMERIC do its thing.
-    elif type(s) != str:
+    elif not isinstance(s, str):
         s=str(s)
     return s
 
-def _stringify_list(l, encoding):
-    return [_stringify(s, encoding) for s in l]
+def _stringify_list(l, encoding, errors='strict'):
+    try:
+        return [_stringify(s, encoding, errors) for s in iter(l)]
+    except TypeError as e:
+        raise csv.Error(str(e))
+
+def _unicodify(s, encoding):
+    if s is None:
+        return None
+    if isinstance(s, (unicode, int, float)):
+        return s
+    elif isinstance(s, str):
+        return s.decode(encoding)
+    return s
 
 class UnicodeWriter(object):
     """
@@ -28,78 +71,127 @@ class UnicodeWriter(object):
     >>> f.seek(0)
     >>> r = unicodecsv.reader(f, encoding='utf-8')
     >>> row = r.next()
-    >>> print row[0], row[1]
-    é ñ
+    >>> row[0] == u'é'
+    True
+    >>> row[1] == u'ñ'
+    True
     """
-    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
-        self.writer = csv.writer(f)
-        self.dialect = dialect
+    def __init__(self, f, dialect=csv.excel, encoding='utf-8', errors='strict',
+                 *args, **kwds):
         self.encoding = encoding
-        self.writer = csv.writer(f, dialect=dialect, **kwds)
+        self.writer = csv.writer(f, dialect, *args, **kwds)
+        self.encoding_errors = errors
 
     def writerow(self, row):
-        self.writer.writerow(_stringify_list(row, self.encoding))
+        self.writer.writerow(_stringify_list(row, self.encoding, self.encoding_errors))
 
     def writerows(self, rows):
         for row in rows:
           self.writerow(row)
+
+    @property
+    def dialect(self):
+        return self.writer.dialect
 writer = UnicodeWriter
 
 class UnicodeReader(object):
-    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
-        self.reader = csv.reader(f, dialect=dialect, **kwds)
+    def __init__(self, f, dialect=None, encoding='utf-8', errors='strict',
+                 **kwds):
+        format_params = ['delimiter', 'doublequote', 'escapechar', 'lineterminator', 'quotechar', 'quoting', 'skipinitialspace']
+        if dialect is None:
+            if not any([kwd_name in format_params for kwd_name in kwds.keys()]):
+                dialect = csv.excel
+        self.reader = csv.reader(f, dialect, **kwds)
         self.encoding = encoding
+        self.encoding_errors = errors
 
     def next(self):
         row = self.reader.next()
-        return [unicode(s, self.encoding) for s in row]
+        encoding = self.encoding
+        encoding_errors = self.encoding_errors
+        float_ = float
+        unicode_ = unicode
+        return [(value if isinstance(value, float_) else
+                 unicode_(value, encoding, encoding_errors)) for value in row]
 
     def __iter__(self):
         return self
+
+    @property
+    def dialect(self):
+        return self.reader.dialect
+
+    @property
+    def line_num(self):
+        return self.reader.line_num
 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'})
+    >>> w = DictWriter(f, ['a', u'ñ', 'b'], restval=u'î')
+    >>> w.writerow({'a':'1', u'ñ':'2'})
+    >>> w.writerow({'a':'1', u'ñ':'2', 'b':u'ø'})
+    >>> w.writerow({'a':u'é', u'ñ':'2'})
     >>> f.seek(0)
-    >>> r = DictReader(f, fieldnames=['a'], restkey='r')
-    >>> r.next() == {'a':u'1', 'r':[u"î"]}
+    >>> r = DictReader(f, fieldnames=['a', u'ñ'], restkey='r')
+    >>> r.next() == {'a': u'1', u'ñ':'2', 'r': [u'î']}
     True
-    >>> r.next() == {'a':u'1', 'r':[u"ø"]}
+    >>> r.next() == {'a': u'1', u'ñ':'2', 'r': [u'\xc3\xb8']}
+    True
+    >>> r.next() == {'a': u'\xc3\xa9', u'ñ':'2', 'r': [u'\xc3\xae']}
     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
+    def __init__(self, csvfile, fieldnames, restval='', extrasaction='raise', dialect='excel', encoding='utf-8', errors='strict', *args, **kwds):
         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)
+        csv.DictWriter.__init__(self, csvfile, fieldnames, restval, extrasaction, dialect, *args, **kwds)
+        self.writer = UnicodeWriter(csvfile, dialect, encoding=encoding, errors=errors, *args, **kwds)
+        self.encoding_errors = errors
+
+    def writeheader(self):
+        fieldnames = _stringify_list(self.fieldnames, self.encoding, self.encoding_errors)
+        header = dict(zip(self.fieldnames, self.fieldnames))
+        self.writerow(header)
 
 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)
+    """
+    >>> from cStringIO import StringIO
+    >>> f = StringIO()
+    >>> w = DictWriter(f, fieldnames=['name', 'place'])
+    >>> w.writerow({'name': 'Cary Grant', 'place': 'hollywood'})
+    >>> w.writerow({'name': 'Nathan Brillstone', 'place': u'øLand'})
+    >>> w.writerow({'name': u'Willam ø. Unicoder', 'place': u'éSpandland'})
+    >>> f.seek(0)
+    >>> r = DictReader(f, fieldnames=['name', 'place'])
+    >>> print r.next() == {'name': 'Cary Grant', 'place': 'hollywood'}
+    True
+    >>> print r.next() == {'name': 'Nathan Brillstone', 'place': u'øLand'}
+    True
+    >>> print r.next() == {'name': u'Willam ø. Unicoder', 'place': u'éSpandland'}
+    True
+    """
+    def __init__(self, csvfile, fieldnames=None, restkey=None, restval=None,
+                 dialect='excel', encoding='utf-8', errors='strict', *args,
+                 **kwds):
+        if fieldnames is not None:
+            fieldnames = _stringify_list(fieldnames, encoding)
+        csv.DictReader.__init__(self, csvfile, fieldnames, restkey, restval, dialect, *args, **kwds)
+        self.reader = UnicodeReader(csvfile, dialect, encoding=encoding,
+                                    errors=errors, *args, **kwds)
+        if fieldnames is None and not hasattr(csv.DictReader, 'fieldnames'):
+            # Python 2.5 fieldnames workaround. (http://bugs.python.org/issue3436)
+            reader = UnicodeReader(csvfile, dialect, encoding=encoding, *args, **kwds)
+            self.fieldnames = _stringify_list(reader.next(), reader.encoding)
+        self.unicode_fieldnames = [_unicodify(f, encoding) for f in
+                                   self.fieldnames]
+        self.unicode_restkey = _unicodify(restkey, encoding)
+
     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
+        row = csv.DictReader.next(self)
+        result = dict((uni_key, row[str_key]) for (str_key, uni_key) in
+                      izip(self.fieldnames, self.unicode_fieldnames))
+        rest = row.get(self.restkey)
+        if rest:
+            result[self.unicode_restkey] = rest
+        return result