BUG: Accept unicode quotechars again in pd.read_csv

Closes pandas-devgh-14477.

Author: gfyoung

doc/source/whatsnew/v0.19.1.txt

@@ -35,6 +35,7 @@ Bug Fixes
 
 
 
+- Bug in ``pd.read_csv`` for Python 2.x in which Unicode quote characters were no longer being respected (:issue:`14477`)
 - Bug in localizing an ambiguous timezone when a boolean is passed (:issue:`14402`)
 - Bug in ``TimedeltaIndex`` addition with a Datetime-like object where addition overflow in the negative direction was not being caught (:issue:`14068`, :issue:`14453`)
 

pandas/compat/__init__.py

@@ -106,6 +106,7 @@ def signature(f):
     reduce = functools.reduce
     long = int
     unichr = chr
+    unicode = str
 
     # This was introduced in Python 3.3, but we don't support
     # Python 3.x < 3.4, so checking PY3 is safe.
@@ -151,6 +152,7 @@ def signature(f):
     reduce = reduce
     long = long
     unichr = unichr
+    unicode = unicode
 
     # Python 2-builtin ranges produce lists
     lrange = builtins.range

pandas/io/tests/parser/quoting.py

@@ -9,7 +9,7 @@
 import pandas.util.testing as tm
 
 from pandas import DataFrame
-from pandas.compat import StringIO
+from pandas.compat import StringIO, u
 
 
 class QuotingTests(object):
@@ -138,3 +138,11 @@ def test_double_quote(self):
         result = self.read_csv(StringIO(data), quotechar='"',
                                doublequote=False)
         tm.assert_frame_equal(result, expected)
+
+    def test_quotechar_unicode(self):
+        # See gh-14477
+        data = 'a\n"1"'
+        expected = DataFrame({'a': [1]})
+
+        result = self.read_csv(StringIO(data), quotechar=u('"'))
+        tm.assert_frame_equal(result, expected)

pandas/parser.pyx

@@ -570,7 +570,8 @@ cdef class TextReader:
         if not QUOTE_MINIMAL <= quoting <= QUOTE_NONE:
             raise TypeError('bad "quoting" value')
 
-        if not isinstance(quote_char, (str, bytes)) and quote_char is not None:
+        if not isinstance(quote_char, (str, compat.unicode,
+                                       bytes)) and quote_char is not None:
             dtype = type(quote_char).__name__
             raise TypeError('"quotechar" must be string, '
                             'not {dtype}'.format(dtype=dtype))