BUG in clipboard (linux, python2) with unicode and separator (GH13747)

doc/source/whatsnew/v0.19.2.txt

@@ -25,3 +25,4 @@ Bug Fixes
 
 - compat with ``dateutil==2.6.0`` for testing (:issue:`14621`)
 - allow ``nanoseconds`` in ``Timestamp.replace`` kwargs (:issue:`14621`)
+- BUG in clipboard (linux, python2) with unicode and separator (:issue:`13747`)

pandas/io/clipboard.py

@@ -1,6 +1,6 @@
 """ io on the clipboard """
 from pandas import compat, get_option, option_context, DataFrame
-from pandas.compat import StringIO
+from pandas.compat import StringIO, PY2
 
 
 def read_clipboard(sep='\s+', **kwargs):  # pragma: no cover
@@ -18,6 +18,14 @@ def read_clipboard(sep='\s+', **kwargs):  # pragma: no cover
     -------
     parsed : DataFrame
     """
+    encoding = kwargs.pop('encoding', 'utf-8')
+
+    # only utf-8 is valid for passed value because that's what clipboard
+    # supports
+    if encoding is not None and encoding.lower().replace('-', '') != 'utf8':
+        raise NotImplementedError(
+            'reading from clipboard only supports utf-8 encoding')
+
     from pandas.util.clipboard import clipboard_get
     from pandas.io.parsers import read_table
     text = clipboard_get()
@@ -78,6 +86,12 @@ def to_clipboard(obj, excel=None, sep=None, **kwargs):  # pragma: no cover
       - Windows:
       - OS X:
     """
+    encoding = kwargs.pop('encoding', 'utf-8')
+
+    # testing if an invalid encoding is passed to clipboard
+    if encoding is not None and encoding.lower().replace('-', '') != 'utf8':
+        raise ValueError('clipboard only supports utf-8 encoding')
+
     from pandas.util.clipboard import clipboard_set
     if excel is None:
         excel = True
@@ -87,8 +101,12 @@ def to_clipboard(obj, excel=None, sep=None, **kwargs):  # pragma: no cover
             if sep is None:
                 sep = '\t'
             buf = StringIO()
-            obj.to_csv(buf, sep=sep, **kwargs)
-            clipboard_set(buf.getvalue())
+            # clipboard_set (pyperclip) expects unicode
+            obj.to_csv(buf, sep=sep, encoding='utf-8', **kwargs)
+            text = buf.getvalue()
+            if PY2:
+                text = text.decode('utf-8')
+            clipboard_set(text)
             return
         except:
             pass

pandas/io/tests/test_clipboard.py

@@ -9,7 +9,7 @@
 from pandas import read_clipboard
 from pandas import get_option
 from pandas.util import testing as tm
-from pandas.util.testing import makeCustomDataframe as mkdf, disabled
+from pandas.util.testing import makeCustomDataframe as mkdf
 
 
 try:
@@ -18,7 +18,6 @@
     raise nose.SkipTest("no clipboard found")
 
 
-@disabled
 class TestClipboard(tm.TestCase):
 
     @classmethod
@@ -52,20 +51,24 @@ def setUpClass(cls):
         # Test for non-ascii text: GH9263
         cls.data['nonascii'] = pd.DataFrame({'en': 'in English'.split(),
                                              'es': 'en español'.split()})
+        # unicode round trip test for GH 13747
+        cls.data['utf8'] = pd.DataFrame({'a': ['µasd', 'Ωœ∑´'],
+                                        'b': ['øπ∆˚¬', 'œ∑´®']})
         cls.data_types = list(cls.data.keys())
 
     @classmethod
     def tearDownClass(cls):
         super(TestClipboard, cls).tearDownClass()
         del cls.data_types, cls.data
 
-    def check_round_trip_frame(self, data_type, excel=None, sep=None):
+    def check_round_trip_frame(self, data_type, excel=None, sep=None,
+                               encoding=None):
         data = self.data[data_type]
-        data.to_clipboard(excel=excel, sep=sep)
+        data.to_clipboard(excel=excel, sep=sep, encoding=encoding)
         if sep is not None:
-            result = read_clipboard(sep=sep, index_col=0)
+            result = read_clipboard(sep=sep, index_col=0, encoding=encoding)
         else:
-            result = read_clipboard()
+            result = read_clipboard(encoding=encoding)
         tm.assert_frame_equal(data, result, check_dtype=False)
 
     def test_round_trip_frame_sep(self):
@@ -115,3 +118,16 @@ def test_read_clipboard_infer_excel(self):
         exp = pd.read_clipboard()
 
         tm.assert_frame_equal(res, exp)
+
+    # test case for testing invalid encoding
+    def test_invalid_encoding(self):
+        data = self.data['string']
+        with tm.assertRaises(ValueError):
+            data.to_clipboard(encoding='ascii')
+        with tm.assertRaises(NotImplementedError):
+            pd.read_clipboard(encoding='ascii')
+
+    def test_round_trip_valid_encodings(self):
+        for enc in ['UTF-8', 'utf-8', 'utf8']:
+            for dt in self.data_types:
+                self.check_round_trip_frame(dt, encoding=enc)