TST: Parser tests refactoring

1) Moved no columns test from CParser-only to `common.py`
2) Moved erroneous placed skiprows tests into their proper place

Author: gfyoung <[email protected]>

Closes pandas-dev#13319 from gfyoung/test-parsers-refactor and squashes the following commits:

bc1402e [gfyoung] TST: Parser tests refactoring

Author: gfyoung

pandas/io/tests/parser/c_parser_only.py

@@ -419,15 +419,6 @@ def test_tokenize_CR_with_quoting(self):
         expected = self.read_csv(StringIO(data.replace('\r', '\n')))
         tm.assert_frame_equal(result, expected)
 
-    def test_raise_on_no_columns(self):
-        # single newline
-        data = "\n"
-        self.assertRaises(ValueError, self.read_csv, StringIO(data))
-
-        # test with more than a single newline
-        data = "\n\n\n"
-        self.assertRaises(ValueError, self.read_csv, StringIO(data))
-
     def test_grow_boundary_at_cap(self):
         # See gh-12494
         #

pandas/io/tests/parser/common.py

@@ -1323,3 +1323,12 @@ def test_inf_parsing(self):
             # TODO: remove condition when 'na_filter' is supported for Python
             df = self.read_csv(StringIO(data), index_col=0, na_filter=False)
             tm.assert_almost_equal(df['A'].values, expected.values)
+
+    def test_raise_on_no_columns(self):
+        # single newline
+        data = "\n"
+        self.assertRaises(EmptyDataError, self.read_csv, StringIO(data))
+
+        # test with more than a single newline
+        data = "\n\n\n"
+        self.assertRaises(EmptyDataError, self.read_csv, StringIO(data))

pandas/io/tests/parser/na_values.py

@@ -223,117 +223,3 @@ def test_na_values_keep_default(self):
                         'Three': ['None', 'two', 'None', 'nan', 'five', '',
                                   'seven']})
         tm.assert_frame_equal(xp.reindex(columns=df.columns), df)
-
-    def test_skiprow_with_newline(self):
-        # see gh-12775 and gh-10911
-        data = """id,text,num_lines
-1,"line 11
-line 12",2
-2,"line 21
-line 22",2
-3,"line 31",1"""
-        expected = [[2, 'line 21\nline 22', 2],
-                    [3, 'line 31', 1]]
-        expected = DataFrame(expected, columns=[
-            'id', 'text', 'num_lines'])
-        df = self.read_csv(StringIO(data), skiprows=[1])
-        tm.assert_frame_equal(df, expected)
-
-        data = ('a,b,c\n~a\n b~,~e\n d~,'
-                '~f\n f~\n1,2,~12\n 13\n 14~')
-        expected = [['a\n b', 'e\n d', 'f\n f']]
-        expected = DataFrame(expected, columns=[
-            'a', 'b', 'c'])
-        df = self.read_csv(StringIO(data),
-                           quotechar="~",
-                           skiprows=[2])
-        tm.assert_frame_equal(df, expected)
-
-        data = ('Text,url\n~example\n '
-                'sentence\n one~,url1\n~'
-                'example\n sentence\n two~,url2\n~'
-                'example\n sentence\n three~,url3')
-        expected = [['example\n sentence\n two', 'url2']]
-        expected = DataFrame(expected, columns=[
-            'Text', 'url'])
-        df = self.read_csv(StringIO(data),
-                           quotechar="~",
-                           skiprows=[1, 3])
-        tm.assert_frame_equal(df, expected)
-
-    def test_skiprow_with_quote(self):
-        # see gh-12775 and gh-10911
-        data = """id,text,num_lines
-1,"line '11' line 12",2
-2,"line '21' line 22",2
-3,"line '31' line 32",1"""
-        expected = [[2, "line '21' line 22", 2],
-                    [3, "line '31' line 32", 1]]
-        expected = DataFrame(expected, columns=[
-            'id', 'text', 'num_lines'])
-        df = self.read_csv(StringIO(data), skiprows=[1])
-        tm.assert_frame_equal(df, expected)
-
-    def test_skiprow_with_newline_and_quote(self):
-        # see gh-12775 and gh-10911
-        data = """id,text,num_lines
-1,"line \n'11' line 12",2
-2,"line \n'21' line 22",2
-3,"line \n'31' line 32",1"""
-        expected = [[2, "line \n'21' line 22", 2],
-                    [3, "line \n'31' line 32", 1]]
-        expected = DataFrame(expected, columns=[
-            'id', 'text', 'num_lines'])
-        df = self.read_csv(StringIO(data), skiprows=[1])
-        tm.assert_frame_equal(df, expected)
-
-        data = """id,text,num_lines
-1,"line '11\n' line 12",2
-2,"line '21\n' line 22",2
-3,"line '31\n' line 32",1"""
-        expected = [[2, "line '21\n' line 22", 2],
-                    [3, "line '31\n' line 32", 1]]
-        expected = DataFrame(expected, columns=[
-            'id', 'text', 'num_lines'])
-        df = self.read_csv(StringIO(data), skiprows=[1])
-        tm.assert_frame_equal(df, expected)
-
-        data = """id,text,num_lines
-1,"line '11\n' \r\tline 12",2
-2,"line '21\n' \r\tline 22",2
-3,"line '31\n' \r\tline 32",1"""
-        expected = [[2, "line '21\n' \r\tline 22", 2],
-                    [3, "line '31\n' \r\tline 32", 1]]
-        expected = DataFrame(expected, columns=[
-            'id', 'text', 'num_lines'])
-        df = self.read_csv(StringIO(data), skiprows=[1])
-        tm.assert_frame_equal(df, expected)
-
-    def test_skiprows_lineterminator(self):
-        # see gh-9079
-        data = '\n'.join(['SMOSMANIA ThetaProbe-ML2X ',
-                          '2007/01/01 01:00   0.2140 U M ',
-                          '2007/01/01 02:00   0.2141 M O ',
-                          '2007/01/01 04:00   0.2142 D M '])
-        expected = DataFrame([['2007/01/01', '01:00', 0.2140, 'U', 'M'],
-                              ['2007/01/01', '02:00', 0.2141, 'M', 'O'],
-                              ['2007/01/01', '04:00', 0.2142, 'D', 'M']],
-                             columns=['date', 'time', 'var', 'flag',
-                                      'oflag'])
-
-        # test with default line terminators "LF" and "CRLF"
-        df = self.read_csv(StringIO(data), skiprows=1, delim_whitespace=True,
-                           names=['date', 'time', 'var', 'flag', 'oflag'])
-        tm.assert_frame_equal(df, expected)
-
-        df = self.read_csv(StringIO(data.replace('\n', '\r\n')),
-                           skiprows=1, delim_whitespace=True,
-                           names=['date', 'time', 'var', 'flag', 'oflag'])
-        tm.assert_frame_equal(df, expected)
-
-        # "CR" is not respected with the Python parser yet
-        if self.engine == 'c':
-            df = self.read_csv(StringIO(data.replace('\n', '\r')),
-                               skiprows=1, delim_whitespace=True,
-                               names=['date', 'time', 'var', 'flag', 'oflag'])
-            tm.assert_frame_equal(df, expected)

pandas/io/tests/parser/skiprows.py

@@ -76,3 +76,117 @@ def test_skiprows_blank(self):
                                     datetime(2000, 1, 3)])
         expected.index.name = 0
         tm.assert_frame_equal(data, expected)
+
+    def test_skiprow_with_newline(self):
+        # see gh-12775 and gh-10911
+        data = """id,text,num_lines
+1,"line 11
+line 12",2
+2,"line 21
+line 22",2
+3,"line 31",1"""
+        expected = [[2, 'line 21\nline 22', 2],
+                    [3, 'line 31', 1]]
+        expected = DataFrame(expected, columns=[
+            'id', 'text', 'num_lines'])
+        df = self.read_csv(StringIO(data), skiprows=[1])
+        tm.assert_frame_equal(df, expected)
+
+        data = ('a,b,c\n~a\n b~,~e\n d~,'
+                '~f\n f~\n1,2,~12\n 13\n 14~')
+        expected = [['a\n b', 'e\n d', 'f\n f']]
+        expected = DataFrame(expected, columns=[
+            'a', 'b', 'c'])
+        df = self.read_csv(StringIO(data),
+                           quotechar="~",
+                           skiprows=[2])
+        tm.assert_frame_equal(df, expected)
+
+        data = ('Text,url\n~example\n '
+                'sentence\n one~,url1\n~'
+                'example\n sentence\n two~,url2\n~'
+                'example\n sentence\n three~,url3')
+        expected = [['example\n sentence\n two', 'url2']]
+        expected = DataFrame(expected, columns=[
+            'Text', 'url'])
+        df = self.read_csv(StringIO(data),
+                           quotechar="~",
+                           skiprows=[1, 3])
+        tm.assert_frame_equal(df, expected)
+
+    def test_skiprow_with_quote(self):
+        # see gh-12775 and gh-10911
+        data = """id,text,num_lines
+1,"line '11' line 12",2
+2,"line '21' line 22",2
+3,"line '31' line 32",1"""
+        expected = [[2, "line '21' line 22", 2],
+                    [3, "line '31' line 32", 1]]
+        expected = DataFrame(expected, columns=[
+            'id', 'text', 'num_lines'])
+        df = self.read_csv(StringIO(data), skiprows=[1])
+        tm.assert_frame_equal(df, expected)
+
+    def test_skiprow_with_newline_and_quote(self):
+        # see gh-12775 and gh-10911
+        data = """id,text,num_lines
+1,"line \n'11' line 12",2
+2,"line \n'21' line 22",2
+3,"line \n'31' line 32",1"""
+        expected = [[2, "line \n'21' line 22", 2],
+                    [3, "line \n'31' line 32", 1]]
+        expected = DataFrame(expected, columns=[
+            'id', 'text', 'num_lines'])
+        df = self.read_csv(StringIO(data), skiprows=[1])
+        tm.assert_frame_equal(df, expected)
+
+        data = """id,text,num_lines
+1,"line '11\n' line 12",2
+2,"line '21\n' line 22",2
+3,"line '31\n' line 32",1"""
+        expected = [[2, "line '21\n' line 22", 2],
+                    [3, "line '31\n' line 32", 1]]
+        expected = DataFrame(expected, columns=[
+            'id', 'text', 'num_lines'])
+        df = self.read_csv(StringIO(data), skiprows=[1])
+        tm.assert_frame_equal(df, expected)
+
+        data = """id,text,num_lines
+1,"line '11\n' \r\tline 12",2
+2,"line '21\n' \r\tline 22",2
+3,"line '31\n' \r\tline 32",1"""
+        expected = [[2, "line '21\n' \r\tline 22", 2],
+                    [3, "line '31\n' \r\tline 32", 1]]
+        expected = DataFrame(expected, columns=[
+            'id', 'text', 'num_lines'])
+        df = self.read_csv(StringIO(data), skiprows=[1])
+        tm.assert_frame_equal(df, expected)
+
+    def test_skiprows_lineterminator(self):
+        # see gh-9079
+        data = '\n'.join(['SMOSMANIA ThetaProbe-ML2X ',
+                          '2007/01/01 01:00   0.2140 U M ',
+                          '2007/01/01 02:00   0.2141 M O ',
+                          '2007/01/01 04:00   0.2142 D M '])
+        expected = DataFrame([['2007/01/01', '01:00', 0.2140, 'U', 'M'],
+                              ['2007/01/01', '02:00', 0.2141, 'M', 'O'],
+                              ['2007/01/01', '04:00', 0.2142, 'D', 'M']],
+                             columns=['date', 'time', 'var', 'flag',
+                                      'oflag'])
+
+        # test with default line terminators "LF" and "CRLF"
+        df = self.read_csv(StringIO(data), skiprows=1, delim_whitespace=True,
+                           names=['date', 'time', 'var', 'flag', 'oflag'])
+        tm.assert_frame_equal(df, expected)
+
+        df = self.read_csv(StringIO(data.replace('\n', '\r\n')),
+                           skiprows=1, delim_whitespace=True,
+                           names=['date', 'time', 'var', 'flag', 'oflag'])
+        tm.assert_frame_equal(df, expected)
+
+        # "CR" is not respected with the Python parser yet
+        if self.engine == 'c':
+            df = self.read_csv(StringIO(data.replace('\n', '\r')),
+                               skiprows=1, delim_whitespace=True,
+                               names=['date', 'time', 'var', 'flag', 'oflag'])
+            tm.assert_frame_equal(df, expected)