From 2c670bd4d3758dfb4f122d6dcd189d5ce048e0d1 Mon Sep 17 00:00:00 2001
From: david-liu-brattle-1
 <36486871+david-liu-brattle-1@users.noreply.github.com>
Date: Mon, 21 May 2018 22:26:39 -0400
Subject: [PATCH 1/7] Refactored clipboard tests

---
 pandas/tests/io/test_clipboard.py | 84 +++++++++++++++++++++++++++----
 1 file changed, 74 insertions(+), 10 deletions(-)

diff --git a/pandas/tests/io/test_clipboard.py b/pandas/tests/io/test_clipboard.py
index 98c0effabec84..6e69e41363caa 100644
--- a/pandas/tests/io/test_clipboard.py
+++ b/pandas/tests/io/test_clipboard.py
@@ -12,7 +12,7 @@
 from pandas.util import testing as tm
 from pandas.util.testing import makeCustomDataframe as mkdf
 from pandas.io.clipboard.exceptions import PyperclipException
-from pandas.io.clipboard import clipboard_set
+from pandas.io.clipboard import clipboard_set, clipboard_get
 
 
 try:
@@ -29,6 +29,7 @@ class TestClipboard(object):
 
     @classmethod
     def setup_class(cls):
+        np.random.seed(0)
         cls.data = {}
         cls.data['string'] = mkdf(5, 3, c_idx_type='s', r_idx_type='i',
                                   c_idx_names=[None], r_idx_names=[None])
@@ -60,7 +61,11 @@ def setup_class(cls):
         # unicode round trip test for GH 13747, GH 12529
         cls.data['utf8'] = pd.DataFrame({'a': ['µasd', 'Ωœ∑´'],
                                          'b': ['øπ∆˚¬', 'œ∑´®']})
+        # Test for quotes and common delimiters in text
+        cls.data['delim_symbols'] = pd.DataFrame({'a': ['"a,\t"b|c', 'd\tef´'],
+                                                  'b': ['hi\'j', 'k\'\'lm']})
         cls.data_types = list(cls.data.keys())
+        cls.data_expected = {}
 
     @classmethod
     def teardown_class(cls):
@@ -70,25 +75,84 @@ 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, encoding=encoding)
-        if sep is not None:
-            result = read_clipboard(sep=sep, index_col=0, encoding=encoding)
-        else:
-            result = read_clipboard(encoding=encoding)
+        result = read_clipboard(sep=sep or '\t', index_col=0,
+                                encoding=encoding)
         tm.assert_frame_equal(data, result, check_dtype=False)
 
+    def test_round_trip_frame(self):
+        for dt in self.data_types:
+            self.check_round_trip_frame(dt)
+
     def test_round_trip_frame_sep(self):
         for dt in self.data_types:
             self.check_round_trip_frame(dt, sep=',')
-            self.check_round_trip_frame(dt, sep=r'\s+')
             self.check_round_trip_frame(dt, sep='|')
+            self.check_round_trip_frame(dt, sep='\t')
 
     def test_round_trip_frame_string(self):
         for dt in self.data_types:
-            self.check_round_trip_frame(dt, excel=False)
-
-    def test_round_trip_frame(self):
+            data = self.data[dt]
+            data.to_clipboard(excel=False, sep=None)
+            result = read_clipboard()
+            assert data.to_string() == result.to_string()
+            assert data.shape == result.shape
+
+    def test_excel_sep_warning(self):
+        with tm.assert_produces_warning():
+            self.data['string'].to_clipboard(excel=True, sep=r'\t')
+
+    @pytest.mark.parametrize('sep, excel', [
+        ('\t', True),
+        (None, True),
+        ('default', True),
+        ('\t', None),
+        (None, None),
+        ('\t', 'default'),
+        (None, 'default')
+        ])
+    def test_clipboard_copy_tabs_default(self, sep, excel):
         for dt in self.data_types:
-            self.check_round_trip_frame(dt)
+            data = self.data[dt]
+            kwargs = {}
+            if excel != 'default':
+                kwargs['excel'] = excel
+            if sep != 'default':
+                kwargs['sep'] = sep
+            data.to_clipboard(**kwargs)
+            assert clipboard_get() == data.to_csv(sep='\t')
+
+    @pytest.mark.parametrize('sep, excel', [
+        (',', True),
+        ('|', True)
+        ])
+    def test_clipboard_copy_delim(self, sep, excel):
+        for dt in self.data_types:
+            data = self.data[dt]
+            kwargs = {}
+            if excel != 'default':
+                kwargs['excel'] = excel
+            if sep != 'default':
+                kwargs['sep'] = sep
+            data.to_clipboard(**kwargs)
+            assert clipboard_get() == data.to_csv(sep=sep)
+
+    @pytest.mark.parametrize('sep, excel', [
+        ('\t', False),
+        (None, False),
+        ('default', False)
+        ])
+    def test_clipboard_copy_strings(self, sep, excel):
+        for dt in self.data_types:
+            data = self.data[dt]
+            kwargs = {}
+            if excel != 'default':
+                kwargs['excel'] = excel
+            if sep != 'default':
+                kwargs['sep'] = sep
+            data.to_clipboard(**kwargs)
+            result = read_clipboard(sep=r'\s+')
+            assert result.to_string() == data.to_string()
+            assert data.shape == result.shape
 
     def test_read_clipboard_infer_excel(self):
         # gh-19010: avoid warnings

From 2470638dadce7bd0e64f5a0c14dbfac9bd824012 Mon Sep 17 00:00:00 2001
From: david-liu-brattle-1
 <36486871+david-liu-brattle-1@users.noreply.github.com>
Date: Mon, 21 May 2018 22:30:56 -0400
Subject: [PATCH 2/7] Code Formatting

---
 pandas/tests/io/test_clipboard.py | 28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

diff --git a/pandas/tests/io/test_clipboard.py b/pandas/tests/io/test_clipboard.py
index 6e69e41363caa..6eab8bb2f1930 100644
--- a/pandas/tests/io/test_clipboard.py
+++ b/pandas/tests/io/test_clipboard.py
@@ -29,7 +29,6 @@ class TestClipboard(object):
 
     @classmethod
     def setup_class(cls):
-        np.random.seed(0)
         cls.data = {}
         cls.data['string'] = mkdf(5, 3, c_idx_type='s', r_idx_type='i',
                                   c_idx_names=[None], r_idx_names=[None])
@@ -65,7 +64,6 @@ def setup_class(cls):
         cls.data['delim_symbols'] = pd.DataFrame({'a': ['"a,\t"b|c', 'd\tef´'],
                                                   'b': ['hi\'j', 'k\'\'lm']})
         cls.data_types = list(cls.data.keys())
-        cls.data_expected = {}
 
     @classmethod
     def teardown_class(cls):
@@ -101,6 +99,14 @@ def test_excel_sep_warning(self):
         with tm.assert_produces_warning():
             self.data['string'].to_clipboard(excel=True, sep=r'\t')
 
+    def build_kwargs(self, sep, excel):
+        kwargs = {}
+        if excel != 'default':
+            kwargs['excel'] = excel
+        if sep != 'default':
+            kwargs['sep'] = sep
+        return kwargs
+
     @pytest.mark.parametrize('sep, excel', [
         ('\t', True),
         (None, True),
@@ -113,11 +119,7 @@ def test_excel_sep_warning(self):
     def test_clipboard_copy_tabs_default(self, sep, excel):
         for dt in self.data_types:
             data = self.data[dt]
-            kwargs = {}
-            if excel != 'default':
-                kwargs['excel'] = excel
-            if sep != 'default':
-                kwargs['sep'] = sep
+            kwargs = self.build_kwargs(sep, excel)
             data.to_clipboard(**kwargs)
             assert clipboard_get() == data.to_csv(sep='\t')
 
@@ -128,11 +130,7 @@ def test_clipboard_copy_tabs_default(self, sep, excel):
     def test_clipboard_copy_delim(self, sep, excel):
         for dt in self.data_types:
             data = self.data[dt]
-            kwargs = {}
-            if excel != 'default':
-                kwargs['excel'] = excel
-            if sep != 'default':
-                kwargs['sep'] = sep
+            kwargs = self.build_kwargs(sep, excel)
             data.to_clipboard(**kwargs)
             assert clipboard_get() == data.to_csv(sep=sep)
 
@@ -144,11 +142,7 @@ def test_clipboard_copy_delim(self, sep, excel):
     def test_clipboard_copy_strings(self, sep, excel):
         for dt in self.data_types:
             data = self.data[dt]
-            kwargs = {}
-            if excel != 'default':
-                kwargs['excel'] = excel
-            if sep != 'default':
-                kwargs['sep'] = sep
+            kwargs = self.build_kwargs(sep, excel)
             data.to_clipboard(**kwargs)
             result = read_clipboard(sep=r'\s+')
             assert result.to_string() == data.to_string()

From ad3c198134820b23aba7c77ae59542cac05608a9 Mon Sep 17 00:00:00 2001
From: david-liu-brattle-1
 <36486871+david-liu-brattle-1@users.noreply.github.com>
Date: Mon, 21 May 2018 22:57:39 -0400
Subject: [PATCH 3/7] PEP8

---
 pandas/tests/io/test_clipboard.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/pandas/tests/io/test_clipboard.py b/pandas/tests/io/test_clipboard.py
index 6eab8bb2f1930..ae7820baf256c 100644
--- a/pandas/tests/io/test_clipboard.py
+++ b/pandas/tests/io/test_clipboard.py
@@ -115,7 +115,7 @@ def build_kwargs(self, sep, excel):
         (None, None),
         ('\t', 'default'),
         (None, 'default')
-        ])
+    ])
     def test_clipboard_copy_tabs_default(self, sep, excel):
         for dt in self.data_types:
             data = self.data[dt]
@@ -126,7 +126,7 @@ def test_clipboard_copy_tabs_default(self, sep, excel):
     @pytest.mark.parametrize('sep, excel', [
         (',', True),
         ('|', True)
-        ])
+    ])
     def test_clipboard_copy_delim(self, sep, excel):
         for dt in self.data_types:
             data = self.data[dt]
@@ -138,7 +138,7 @@ def test_clipboard_copy_delim(self, sep, excel):
         ('\t', False),
         (None, False),
         ('default', False)
-        ])
+    ])
     def test_clipboard_copy_strings(self, sep, excel):
         for dt in self.data_types:
             data = self.data[dt]

From bfba15c678e4870e9bc91734fe98e7f775ecf2b9 Mon Sep 17 00:00:00 2001
From: david-liu-brattle-1 <david.liu@brattle.com>
Date: Tue, 5 Jun 2018 22:13:35 -0400
Subject: [PATCH 4/7] Refactored tests

---
 pandas/tests/io/test_clipboard.py | 217 ++++++++++++++----------------
 1 file changed, 102 insertions(+), 115 deletions(-)

diff --git a/pandas/tests/io/test_clipboard.py b/pandas/tests/io/test_clipboard.py
index ae7820baf256c..17b469786a1fe 100644
--- a/pandas/tests/io/test_clipboard.py
+++ b/pandas/tests/io/test_clipboard.py
@@ -22,131 +22,118 @@
     _DEPS_INSTALLED = 0
 
 
+def build_kwargs(sep, excel):
+    kwargs = {}
+    if excel != 'default':
+        kwargs['excel'] = excel
+    if sep != 'default':
+        kwargs['sep'] = sep
+    return kwargs
+
+
+def gen_df(data_type):
+    if data_type == 'delims':
+        return pd.DataFrame({'a': ['"a,\t"b|c', 'd\tef´'],
+                             'b': ['hi\'j', 'k\'\'lm']})
+    elif data_type == 'utf8':
+        return pd.DataFrame({'a': ['µasd', 'Ωœ∑´'],
+                             'b': ['øπ∆˚¬', 'œ∑´®']})
+    elif data_type == 'string':
+        return mkdf(5, 3, c_idx_type='s', r_idx_type='i',
+                    c_idx_names=[None], r_idx_names=[None])
+    elif data_type == 'long':
+        max_rows = get_option('display.max_rows')
+        return mkdf(max_rows + 1, 3,
+                    data_gen_f=lambda *args: randint(2),
+                    c_idx_type='s', r_idx_type='i',
+                    c_idx_names=[None], r_idx_names=[None])
+    elif data_type == 'nonascii':
+        return pd.DataFrame({'en': 'in English'.split(),
+                             'es': 'en español'.split()})
+    elif data_type == 'colwidth':
+        _cw = get_option('display.max_colwidth') + 1
+        return mkdf(5, 3, data_gen_f=lambda *args: 'x' * _cw,
+                    c_idx_type='s', r_idx_type='i',
+                    c_idx_names=[None], r_idx_names=[None])
+    elif data_type == 'mixed':
+        return DataFrame({'a': np.arange(1.0, 6.0) + 0.01,
+                          'b': np.arange(1, 6),
+                          'c': list('abcde')})
+    elif data_type == 'float':
+        return mkdf(5, 3, data_gen_f=lambda r, c: float(r) + 0.01,
+                    c_idx_type='s', r_idx_type='i',
+                    c_idx_names=[None], r_idx_names=[None])
+
+    elif data_type == 'int':
+        return mkdf(5, 3, data_gen_f=lambda *args: randint(2),
+                    c_idx_type='s', r_idx_type='i',
+                    c_idx_names=[None], r_idx_names=[None])
+
+
+@pytest.fixture(params=['delims', 'utf8', 'string', 'long', 'nonascii',
+                        'colwidth', 'mixed', 'float', 'int'])
+def df(request):
+    return gen_df(request.param)
+
+
 @pytest.mark.single
 @pytest.mark.skipif(not _DEPS_INSTALLED,
                     reason="clipboard primitives not installed")
 class TestClipboard(object):
 
-    @classmethod
-    def setup_class(cls):
-        cls.data = {}
-        cls.data['string'] = mkdf(5, 3, c_idx_type='s', r_idx_type='i',
-                                  c_idx_names=[None], r_idx_names=[None])
-        cls.data['int'] = mkdf(5, 3, data_gen_f=lambda *args: randint(2),
-                               c_idx_type='s', r_idx_type='i',
-                               c_idx_names=[None], r_idx_names=[None])
-        cls.data['float'] = mkdf(5, 3,
-                                 data_gen_f=lambda r, c: float(r) + 0.01,
-                                 c_idx_type='s', r_idx_type='i',
-                                 c_idx_names=[None], r_idx_names=[None])
-        cls.data['mixed'] = DataFrame({'a': np.arange(1.0, 6.0) + 0.01,
-                                       'b': np.arange(1, 6),
-                                       'c': list('abcde')})
-
-        # Test columns exceeding "max_colwidth" (GH8305)
-        _cw = get_option('display.max_colwidth') + 1
-        cls.data['colwidth'] = mkdf(5, 3, data_gen_f=lambda *args: 'x' * _cw,
-                                    c_idx_type='s', r_idx_type='i',
-                                    c_idx_names=[None], r_idx_names=[None])
-        # Test GH-5346
-        max_rows = get_option('display.max_rows')
-        cls.data['longdf'] = mkdf(max_rows + 1, 3,
-                                  data_gen_f=lambda *args: randint(2),
-                                  c_idx_type='s', r_idx_type='i',
-                                  c_idx_names=[None], r_idx_names=[None])
-        # 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, GH 12529
-        cls.data['utf8'] = pd.DataFrame({'a': ['µasd', 'Ωœ∑´'],
-                                         'b': ['øπ∆˚¬', 'œ∑´®']})
-        # Test for quotes and common delimiters in text
-        cls.data['delim_symbols'] = pd.DataFrame({'a': ['"a,\t"b|c', 'd\tef´'],
-                                                  'b': ['hi\'j', 'k\'\'lm']})
-        cls.data_types = list(cls.data.keys())
-
-    @classmethod
-    def teardown_class(cls):
-        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, excel=None, sep=None,
                                encoding=None):
-        data = self.data[data_type]
         data.to_clipboard(excel=excel, sep=sep, encoding=encoding)
         result = read_clipboard(sep=sep or '\t', index_col=0,
                                 encoding=encoding)
         tm.assert_frame_equal(data, result, check_dtype=False)
 
-    def test_round_trip_frame(self):
-        for dt in self.data_types:
-            self.check_round_trip_frame(dt)
+    @pytest.mark.xfail
+    def test_round_trip_frame(self, df):
+        self.check_round_trip_frame(df)
 
-    def test_round_trip_frame_sep(self):
-        for dt in self.data_types:
-            self.check_round_trip_frame(dt, sep=',')
-            self.check_round_trip_frame(dt, sep='|')
-            self.check_round_trip_frame(dt, sep='\t')
+    def test_round_trip_frame_sep(self, df):
+        self.check_round_trip_frame(df, sep=',')
+        self.check_round_trip_frame(df, sep='|')
+        self.check_round_trip_frame(df, sep='\t')
 
-    def test_round_trip_frame_string(self):
-        for dt in self.data_types:
-            data = self.data[dt]
-            data.to_clipboard(excel=False, sep=None)
-            result = read_clipboard()
-            assert data.to_string() == result.to_string()
-            assert data.shape == result.shape
+    @pytest.mark.xfail
+    def test_round_trip_frame_string(self, df):
+        df.to_clipboard(excel=False, sep=None)
+        result = read_clipboard()
+        assert df.to_string() == result.to_string()
+        assert df.shape == result.shape
 
+    @pytest.mark.xfail
     def test_excel_sep_warning(self):
         with tm.assert_produces_warning():
-            self.data['string'].to_clipboard(excel=True, sep=r'\t')
-
-    def build_kwargs(self, sep, excel):
-        kwargs = {}
-        if excel != 'default':
-            kwargs['excel'] = excel
-        if sep != 'default':
-            kwargs['sep'] = sep
-        return kwargs
-
-    @pytest.mark.parametrize('sep, excel', [
-        ('\t', True),
-        (None, True),
-        ('default', True),
-        ('\t', None),
-        (None, None),
-        ('\t', 'default'),
-        (None, 'default')
-    ])
-    def test_clipboard_copy_tabs_default(self, sep, excel):
-        for dt in self.data_types:
-            data = self.data[dt]
-            kwargs = self.build_kwargs(sep, excel)
-            data.to_clipboard(**kwargs)
-            assert clipboard_get() == data.to_csv(sep='\t')
-
-    @pytest.mark.parametrize('sep, excel', [
-        (',', True),
-        ('|', True)
-    ])
-    def test_clipboard_copy_delim(self, sep, excel):
-        for dt in self.data_types:
-            data = self.data[dt]
-            kwargs = self.build_kwargs(sep, excel)
-            data.to_clipboard(**kwargs)
-            assert clipboard_get() == data.to_csv(sep=sep)
-
-    @pytest.mark.parametrize('sep, excel', [
-        ('\t', False),
-        (None, False),
-        ('default', False)
-    ])
-    def test_clipboard_copy_strings(self, sep, excel):
-        for dt in self.data_types:
-            data = self.data[dt]
-            kwargs = self.build_kwargs(sep, excel)
-            data.to_clipboard(**kwargs)
-            result = read_clipboard(sep=r'\s+')
-            assert result.to_string() == data.to_string()
-            assert data.shape == result.shape
+            gen_df('string').to_clipboard(excel=True, sep=r'\t')
+
+    @pytest.mark.xfail
+    @pytest.mark.parametrize('sep', ['\t', None, 'default'])
+    @pytest.mark.parametrize('excel', [True, None, 'default'])
+    def test_clipboard_copy_tabs_default(self, sep, excel, df):
+        kwargs = build_kwargs(sep, excel)
+        df.to_clipboard(**kwargs)
+        assert clipboard_get() == df.to_csv(sep='\t')
+
+    @pytest.mark.xfail
+    @pytest.mark.parametrize('sep', [',', '|'])
+    @pytest.mark.parametrize('excel', [True])
+    def test_clipboard_copy_delim(self, sep, excel, df):
+        kwargs = build_kwargs(sep, excel)
+        df.to_clipboard(**kwargs)
+        assert clipboard_get() == df.to_csv(sep=sep)
+
+    @pytest.mark.xfail
+    @pytest.mark.parametrize('sep', ['\t', None, 'default'])
+    @pytest.mark.parametrize('excel', [False])
+    def test_clipboard_copy_strings(self, sep, excel, df):
+        kwargs = build_kwargs(sep, excel)
+        df.to_clipboard(**kwargs)
+        result = read_clipboard(sep=r'\s+')
+        assert result.to_string() == df.to_string()
+        assert df.shape == result.shape
 
     def test_read_clipboard_infer_excel(self):
         # gh-19010: avoid warnings
@@ -184,13 +171,13 @@ def test_read_clipboard_infer_excel(self):
 
     def test_invalid_encoding(self):
         # test case for testing invalid encoding
-        data = self.data['string']
+        df = gen_df('string')
         with pytest.raises(ValueError):
-            data.to_clipboard(encoding='ascii')
+            df.to_clipboard(encoding='ascii')
         with pytest.raises(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)
+    @pytest.mark.xfail
+    @pytest.mark.parametrize('enc', ['UTF-8', 'utf-8', 'utf8'])
+    def test_round_trip_valid_encodings(self, enc, df):
+        self.check_round_trip_frame(df, encoding=enc)

From 7888f83bbbbb39324315fbf4a8abd137cc24e184 Mon Sep 17 00:00:00 2001
From: david-liu-brattle-1 <david.liu@brattle.com>
Date: Sat, 23 Jun 2018 15:07:11 -0400
Subject: [PATCH 5/7] Commented tests

---
 pandas/tests/io/test_clipboard.py | 56 ++++++++++++++++++++++---------
 1 file changed, 40 insertions(+), 16 deletions(-)

diff --git a/pandas/tests/io/test_clipboard.py b/pandas/tests/io/test_clipboard.py
index 17b469786a1fe..70bdbd1d950ce 100644
--- a/pandas/tests/io/test_clipboard.py
+++ b/pandas/tests/io/test_clipboard.py
@@ -9,6 +9,7 @@
 from pandas import DataFrame
 from pandas import read_clipboard
 from pandas import get_option
+from pandas.compat import PY2
 from pandas.util import testing as tm
 from pandas.util.testing import makeCustomDataframe as mkdf
 from pandas.io.clipboard.exceptions import PyperclipException
@@ -63,7 +64,6 @@ def gen_df(data_type):
         return mkdf(5, 3, data_gen_f=lambda r, c: float(r) + 0.01,
                     c_idx_type='s', r_idx_type='i',
                     c_idx_names=[None], r_idx_names=[None])
-
     elif data_type == 'int':
         return mkdf(5, 3, data_gen_f=lambda *args: randint(2),
                     c_idx_type='s', r_idx_type='i',
@@ -88,15 +88,22 @@ def check_round_trip_frame(self, data, excel=None, sep=None,
                                 encoding=encoding)
         tm.assert_frame_equal(data, result, check_dtype=False)
 
+    # Test that default arguments copy as tab delimited
+    # Fails because to_clipboard defaults to space delim.
+    # Issue in #21104, Fixed in #21111
     @pytest.mark.xfail
     def test_round_trip_frame(self, df):
         self.check_round_trip_frame(df)
 
-    def test_round_trip_frame_sep(self, df):
-        self.check_round_trip_frame(df, sep=',')
-        self.check_round_trip_frame(df, sep='|')
-        self.check_round_trip_frame(df, sep='\t')
+    # Test that explicit delimiters are respected
+    @pytest.mark.parametrize('sep', ['\t', ',', '|'])
+    def test_round_trip_frame_sep(self, df, sep):
+        self.check_round_trip_frame(df, sep=sep)
 
+    # Test white space separator
+    # Fails on 'delims' df because quote escapes aren't handled correctly
+    # in default c engine. Fixed in #21111 by defaulting to python engine
+    # for whitespace separator
     @pytest.mark.xfail
     def test_round_trip_frame_string(self, df):
         df.to_clipboard(excel=False, sep=None)
@@ -104,29 +111,44 @@ def test_round_trip_frame_string(self, df):
         assert df.to_string() == result.to_string()
         assert df.shape == result.shape
 
+    # Two character separator is not supported in to_clipboard
+    # Test that multi-character separators are not silently passed
+    # Fails, Fixed in #21111
     @pytest.mark.xfail
     def test_excel_sep_warning(self):
         with tm.assert_produces_warning():
             gen_df('string').to_clipboard(excel=True, sep=r'\t')
 
+    # Separator is ignored when excel=False and should produce a warning
+    # Fails, Fixed in #21111
+    @pytest.mark.xfail
+    def test_copy_delim_warning(self):
+        with tm.assert_produces_warning():
+            gen_df('string').to_clipboard(excel=False, sep='\t')
+
+    # Tests that the default behavior of to_clipboard is tab
+    # delimited and excel="True"
+    # Fails because to_clipboard defaults to space delim.
+    # Issue in #21104, Fixed in #21111
     @pytest.mark.xfail
     @pytest.mark.parametrize('sep', ['\t', None, 'default'])
     @pytest.mark.parametrize('excel', [True, None, 'default'])
     def test_clipboard_copy_tabs_default(self, sep, excel, df):
         kwargs = build_kwargs(sep, excel)
         df.to_clipboard(**kwargs)
-        assert clipboard_get() == df.to_csv(sep='\t')
-
-    @pytest.mark.xfail
-    @pytest.mark.parametrize('sep', [',', '|'])
-    @pytest.mark.parametrize('excel', [True])
-    def test_clipboard_copy_delim(self, sep, excel, df):
-        kwargs = build_kwargs(sep, excel)
-        df.to_clipboard(**kwargs)
-        assert clipboard_get() == df.to_csv(sep=sep)
-
+        if PY2:
+            # to_clipboard copies unicode, to_csv produces bytes. This is 
+            # expected behavior
+            assert clipboard_get().encode('utf-8') == df.to_csv(sep='\t')
+        else:
+            assert clipboard_get() == df.to_csv(sep='\t')
+
+    # Tests reading of white space separated tables
+    # Fails on 'delims' df because quote escapes aren't handled correctly
+    # in default c engine. Fixed in #21111 by defaulting to python engine
+    # for whitespace separator
     @pytest.mark.xfail
-    @pytest.mark.parametrize('sep', ['\t', None, 'default'])
+    @pytest.mark.parametrize('sep', [None, 'default'])
     @pytest.mark.parametrize('excel', [False])
     def test_clipboard_copy_strings(self, sep, excel, df):
         kwargs = build_kwargs(sep, excel)
@@ -177,6 +199,8 @@ def test_invalid_encoding(self):
         with pytest.raises(NotImplementedError):
             pd.read_clipboard(encoding='ascii')
 
+    # Fails because to_clipboard defaults to space delim.
+    # Issue in #21104, Fixed in #21111
     @pytest.mark.xfail
     @pytest.mark.parametrize('enc', ['UTF-8', 'utf-8', 'utf8'])
     def test_round_trip_valid_encodings(self, enc, df):

From 5f4baa37bc7052f933872890fa3ff05077f54cac Mon Sep 17 00:00:00 2001
From: david-liu-brattle-1 <david.liu@brattle.com>
Date: Tue, 26 Jun 2018 11:11:37 -0400
Subject: [PATCH 6/7] xfail reasons

---
 pandas/tests/io/test_clipboard.py | 36 ++++++++++++++-----------------
 1 file changed, 16 insertions(+), 20 deletions(-)

diff --git a/pandas/tests/io/test_clipboard.py b/pandas/tests/io/test_clipboard.py
index 70bdbd1d950ce..d33aa4756744a 100644
--- a/pandas/tests/io/test_clipboard.py
+++ b/pandas/tests/io/test_clipboard.py
@@ -89,9 +89,8 @@ def check_round_trip_frame(self, data, excel=None, sep=None,
         tm.assert_frame_equal(data, result, check_dtype=False)
 
     # Test that default arguments copy as tab delimited
-    # Fails because to_clipboard defaults to space delim.
-    # Issue in #21104, Fixed in #21111
-    @pytest.mark.xfail
+    @pytest.mark.xfail(reason='to_clipboard defaults to space delim. '
+                       'Issue in #21104, Fixed in #21111')
     def test_round_trip_frame(self, df):
         self.check_round_trip_frame(df)
 
@@ -101,10 +100,10 @@ def test_round_trip_frame_sep(self, df, sep):
         self.check_round_trip_frame(df, sep=sep)
 
     # Test white space separator
-    # Fails on 'delims' df because quote escapes aren't handled correctly
-    # in default c engine. Fixed in #21111 by defaulting to python engine
-    # for whitespace separator
-    @pytest.mark.xfail
+    @pytest.mark.xfail(reason="Fails on 'delims' df because quote escapes "
+                       "aren't handled correctly in default c engine. Fixed "
+                       "in #21111 by defaulting to python engine for "
+                       "whitespace separator")
     def test_round_trip_frame_string(self, df):
         df.to_clipboard(excel=False, sep=None)
         result = read_clipboard()
@@ -113,8 +112,7 @@ def test_round_trip_frame_string(self, df):
 
     # Two character separator is not supported in to_clipboard
     # Test that multi-character separators are not silently passed
-    # Fails, Fixed in #21111
-    @pytest.mark.xfail
+    @pytest.mark.xfail(reason="Not yet implemented.  Fixed in #21111")
     def test_excel_sep_warning(self):
         with tm.assert_produces_warning():
             gen_df('string').to_clipboard(excel=True, sep=r'\t')
@@ -128,26 +126,25 @@ def test_copy_delim_warning(self):
 
     # Tests that the default behavior of to_clipboard is tab
     # delimited and excel="True"
-    # Fails because to_clipboard defaults to space delim.
-    # Issue in #21104, Fixed in #21111
-    @pytest.mark.xfail
+    @pytest.mark.xfail(reason="to_clipboard defaults to space delim. Issue in "
+                       "#21104, Fixed in #21111")
     @pytest.mark.parametrize('sep', ['\t', None, 'default'])
     @pytest.mark.parametrize('excel', [True, None, 'default'])
     def test_clipboard_copy_tabs_default(self, sep, excel, df):
         kwargs = build_kwargs(sep, excel)
         df.to_clipboard(**kwargs)
         if PY2:
-            # to_clipboard copies unicode, to_csv produces bytes. This is 
+            # to_clipboard copies unicode, to_csv produces bytes. This is
             # expected behavior
             assert clipboard_get().encode('utf-8') == df.to_csv(sep='\t')
         else:
             assert clipboard_get() == df.to_csv(sep='\t')
 
     # Tests reading of white space separated tables
-    # Fails on 'delims' df because quote escapes aren't handled correctly
-    # in default c engine. Fixed in #21111 by defaulting to python engine
-    # for whitespace separator
-    @pytest.mark.xfail
+    @pytest.mark.xfail(reason="Fails on 'delims' df because quote escapes "
+                       "aren't handled correctly. in default c engine. Fixed "
+                       "in #21111 by defaulting to python engine for "
+                       "whitespace separator")
     @pytest.mark.parametrize('sep', [None, 'default'])
     @pytest.mark.parametrize('excel', [False])
     def test_clipboard_copy_strings(self, sep, excel, df):
@@ -199,9 +196,8 @@ def test_invalid_encoding(self):
         with pytest.raises(NotImplementedError):
             pd.read_clipboard(encoding='ascii')
 
-    # Fails because to_clipboard defaults to space delim.
-    # Issue in #21104, Fixed in #21111
-    @pytest.mark.xfail
+    @pytest.mark.xfail(reason='to_clipboard defaults to space delim. '
+                       'Issue in #21104, Fixed in #21111')
     @pytest.mark.parametrize('enc', ['UTF-8', 'utf-8', 'utf8'])
     def test_round_trip_valid_encodings(self, enc, df):
         self.check_round_trip_frame(df, encoding=enc)

From 2613a06ca8a7d6ecee37b9353626645ed3da3a74 Mon Sep 17 00:00:00 2001
From: david-liu-brattle-1 <david.liu@brattle.com>
Date: Tue, 26 Jun 2018 13:42:29 -0400
Subject: [PATCH 7/7] Cleaned fixture organization

---
 pandas/tests/io/test_clipboard.py | 29 +++++++++++++----------------
 1 file changed, 13 insertions(+), 16 deletions(-)

diff --git a/pandas/tests/io/test_clipboard.py b/pandas/tests/io/test_clipboard.py
index d33aa4756744a..80fddd50fc9a8 100644
--- a/pandas/tests/io/test_clipboard.py
+++ b/pandas/tests/io/test_clipboard.py
@@ -32,7 +32,11 @@ def build_kwargs(sep, excel):
     return kwargs
 
 
-def gen_df(data_type):
+@pytest.fixture(params=['delims', 'utf8', 'string', 'long', 'nonascii',
+                        'colwidth', 'mixed', 'float', 'int'])
+def df(request):
+    data_type = request.param
+
     if data_type == 'delims':
         return pd.DataFrame({'a': ['"a,\t"b|c', 'd\tef´'],
                              'b': ['hi\'j', 'k\'\'lm']})
@@ -68,19 +72,14 @@ def gen_df(data_type):
         return mkdf(5, 3, data_gen_f=lambda *args: randint(2),
                     c_idx_type='s', r_idx_type='i',
                     c_idx_names=[None], r_idx_names=[None])
-
-
-@pytest.fixture(params=['delims', 'utf8', 'string', 'long', 'nonascii',
-                        'colwidth', 'mixed', 'float', 'int'])
-def df(request):
-    return gen_df(request.param)
+    else:
+        raise ValueError
 
 
 @pytest.mark.single
 @pytest.mark.skipif(not _DEPS_INSTALLED,
                     reason="clipboard primitives not installed")
 class TestClipboard(object):
-
     def check_round_trip_frame(self, data, excel=None, sep=None,
                                encoding=None):
         data.to_clipboard(excel=excel, sep=sep, encoding=encoding)
@@ -113,16 +112,15 @@ def test_round_trip_frame_string(self, df):
     # Two character separator is not supported in to_clipboard
     # Test that multi-character separators are not silently passed
     @pytest.mark.xfail(reason="Not yet implemented.  Fixed in #21111")
-    def test_excel_sep_warning(self):
+    def test_excel_sep_warning(self, df):
         with tm.assert_produces_warning():
-            gen_df('string').to_clipboard(excel=True, sep=r'\t')
+            df.to_clipboard(excel=True, sep=r'\t')
 
     # Separator is ignored when excel=False and should produce a warning
-    # Fails, Fixed in #21111
-    @pytest.mark.xfail
-    def test_copy_delim_warning(self):
+    @pytest.mark.xfail(reason="Not yet implemented.  Fixed in #21111")
+    def test_copy_delim_warning(self, df):
         with tm.assert_produces_warning():
-            gen_df('string').to_clipboard(excel=False, sep='\t')
+            df.to_clipboard(excel=False, sep='\t')
 
     # Tests that the default behavior of to_clipboard is tab
     # delimited and excel="True"
@@ -188,9 +186,8 @@ def test_read_clipboard_infer_excel(self):
 
         tm.assert_frame_equal(res, exp)
 
-    def test_invalid_encoding(self):
+    def test_invalid_encoding(self, df):
         # test case for testing invalid encoding
-        df = gen_df('string')
         with pytest.raises(ValueError):
             df.to_clipboard(encoding='ascii')
         with pytest.raises(NotImplementedError):