From 7600e12128d7ea39eb935eb0a2469bd5d3108ef5 Mon Sep 17 00:00:00 2001 From: Pooja Subramaniam Date: Tue, 17 Jan 2023 22:07:36 +0100 Subject: [PATCH 1/5] adding test to check if rows are skipped when skip_blank_lines is set to true in read_csv --- .../io/parser/common/test_common_basic.py | 24 +++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/pandas/tests/io/parser/common/test_common_basic.py b/pandas/tests/io/parser/common/test_common_basic.py index 6656face3be84..c5cfa7ae70c55 100644 --- a/pandas/tests/io/parser/common/test_common_basic.py +++ b/pandas/tests/io/parser/common/test_common_basic.py @@ -862,3 +862,27 @@ def test_read_seek(all_parsers): actual = parser.read_csv(file) expected = parser.read_csv(StringIO(content)) tm.assert_frame_equal(actual, expected) + + +@xfail_pyarrow +def test_read_csv_skip_blank_rows(all_parsers): + # GH22693 + parser = all_parsers + csv_f = StringIO( + """A, B, C, D + FOO, 1, 2, 3 + FOO, 4, 5, 6 + , , , + FOO, 7, 8, 9 + , 10, 11, 12 + , , , + """ + ) + + result = parser.read_csv(csv_f, skip_blank_lines=True) + expected = DataFrame( + [["FOO", 1, 2, 3], ["FOO", 4, 5, 6], ["FOO", 7, 8, 9], [np.nan, 10, 11, 12]], + columns=["A", "B", "C", "D"], + ) + + tm.assert_frame_equal(result, expected) From e5cbc2c901ec0d55c372c3046ab3165876995323 Mon Sep 17 00:00:00 2001 From: Pooja Subramaniam Date: Sat, 21 Jan 2023 11:08:30 +0100 Subject: [PATCH 2/5] changed xfail_pyarrow to pytest.mark.fail --- pandas/tests/io/parser/common/test_common_basic.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pandas/tests/io/parser/common/test_common_basic.py b/pandas/tests/io/parser/common/test_common_basic.py index c5cfa7ae70c55..007cd040a2a4a 100644 --- a/pandas/tests/io/parser/common/test_common_basic.py +++ b/pandas/tests/io/parser/common/test_common_basic.py @@ -864,7 +864,7 @@ def test_read_seek(all_parsers): tm.assert_frame_equal(actual, expected) -@xfail_pyarrow +@pytest.mark.xfail def test_read_csv_skip_blank_rows(all_parsers): # GH22693 parser = all_parsers From 278f1a808a8b031b688b33aaacd7b812be7c73c2 Mon Sep 17 00:00:00 2001 From: Pooja Subramaniam Date: Tue, 31 Jan 2023 20:48:10 +0100 Subject: [PATCH 3/5] corrected indent --- pandas/tests/io/parser/common/test_common_basic.py | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/pandas/tests/io/parser/common/test_common_basic.py b/pandas/tests/io/parser/common/test_common_basic.py index 007cd040a2a4a..6530369f5ca1f 100644 --- a/pandas/tests/io/parser/common/test_common_basic.py +++ b/pandas/tests/io/parser/common/test_common_basic.py @@ -870,13 +870,13 @@ def test_read_csv_skip_blank_rows(all_parsers): parser = all_parsers csv_f = StringIO( """A, B, C, D - FOO, 1, 2, 3 - FOO, 4, 5, 6 - , , , - FOO, 7, 8, 9 - , 10, 11, 12 - , , , - """ + FOO, 1, 2, 3 + FOO, 4, 5, 6 + , , , + FOO, 7, 8, 9 + , 10, 11, 12 + , , , + """ ) result = parser.read_csv(csv_f, skip_blank_lines=True) From 43e348fb91973ba73c6b5a633617c5ef3a9cc99f Mon Sep 17 00:00:00 2001 From: Pooja Subramaniam Date: Thu, 2 Feb 2023 22:21:17 +0100 Subject: [PATCH 4/5] indenting further behind --- .../tests/io/parser/common/test_common_basic.py | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/pandas/tests/io/parser/common/test_common_basic.py b/pandas/tests/io/parser/common/test_common_basic.py index 6530369f5ca1f..8ed5f3b6ad9d0 100644 --- a/pandas/tests/io/parser/common/test_common_basic.py +++ b/pandas/tests/io/parser/common/test_common_basic.py @@ -869,14 +869,14 @@ def test_read_csv_skip_blank_rows(all_parsers): # GH22693 parser = all_parsers csv_f = StringIO( - """A, B, C, D - FOO, 1, 2, 3 - FOO, 4, 5, 6 - , , , - FOO, 7, 8, 9 - , 10, 11, 12 - , , , - """ +"""A, B, C, D +FOO, 1, 2, 3 +FOO, 4, 5, 6 +,,, +FOO, 7, 8, 9 +, 10, 11, 12 +,,, +""" ) result = parser.read_csv(csv_f, skip_blank_lines=True) From 8bb131047d92a523baf00b0306c39b44c14e1d1f Mon Sep 17 00:00:00 2001 From: Pooja Subramaniam Date: Wed, 15 Feb 2023 16:08:30 +0100 Subject: [PATCH 5/5] pre-commit fix --- pandas/tests/io/parser/common/test_common_basic.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pandas/tests/io/parser/common/test_common_basic.py b/pandas/tests/io/parser/common/test_common_basic.py index 8ed5f3b6ad9d0..86d3557d89c1f 100644 --- a/pandas/tests/io/parser/common/test_common_basic.py +++ b/pandas/tests/io/parser/common/test_common_basic.py @@ -869,7 +869,7 @@ def test_read_csv_skip_blank_rows(all_parsers): # GH22693 parser = all_parsers csv_f = StringIO( -"""A, B, C, D + """A, B, C, D FOO, 1, 2, 3 FOO, 4, 5, 6 ,,,