BUG: read_csv with pyarrow engine cannot handle single-line CSV files

[khemkaran10]

Before Fix:

>>> pd.read_csv(
...     io.StringIO("1,2,3"),
...     names=["col1", "col2", "col3"],
...     engine="pyarrow",
... )
---------------------------------------------------------------------------
ArrowInvalid     
...
ParserError: CSV parse error: Empty CSV file or block: cannot infer number of columns

After Fix:

>>> pd.read_csv(
...     io.StringIO("1,2,3"),
...     names=["col1", "col2", "col3"],
...     engine="pyarrow",
... )
---------------------------------------------------------------------------
    col1  col2  col3
0     1     2     3

• Fixed read_csv (Pyarrow) issue with the single line csv files by setting the column_names argument in read_options.

• closes BUG: read_csv with pyarrow engine cannot handle single-line CSV files #62635 (Replace xxxx with the GitHub issue number)

• Tests added and passed if fixing a bug or adding a new feature

• All code checks passed.

[Alvaro-Kothe]

There are some tests that is skipping pyarrow because of this. Can you try to remove the skip?

pandas/pandas/tests/io/parser/common/test_float.py

Lines 23 to 31 in 1863adb

	@skip_pyarrow # ParserError: CSV parse error: Empty CSV file or block
	def test_float_parser(all_parsers):
	# see gh-9565
	parser = all_parsers
	data = "45e-1,4.5,45.,inf,-inf"
	result = parser.read_csv(StringIO(data), header=None)
	expected = DataFrame([[float(s) for s in data.split(",")]])
	tm.assert_frame_equal(result, expected)

pandas/pandas/tests/io/parser/common/test_ints.py

Lines 187 to 229 in 1863adb

	@skip_pyarrow # CSV parse error: Empty CSV file or block
	@pytest.mark.parametrize(
	"val", [np.iinfo(np.uint64).max, np.iinfo(np.int64).max, np.iinfo(np.int64).min]
	)
	def test_int64_uint64_range(all_parsers, val):
	# These numbers fall right inside the int64-uint64
	# range, so they should be parsed as integer.
	parser = all_parsers
	result = parser.read_csv(StringIO(str(val)), header=None)
	expected = DataFrame([val])
	tm.assert_frame_equal(result, expected)
	@skip_pyarrow # CSV parse error: Empty CSV file or block
	@pytest.mark.parametrize(
	"val", [np.iinfo(np.uint64).max + 1, np.iinfo(np.int64).min - 1]
	)
	def test_outside_int64_uint64_range(all_parsers, val, request):
	# These numbers fall just outside the int64-uint64
	# range, so they should be parsed as object.
	parser = all_parsers
	if parser.engine == "python":
	mark = pytest.mark.xfail(reason="TODO: Python engine reads bigint as string")
	request.applymarker(mark)
	result = parser.read_csv(StringIO(str(val)), header=None)
	expected = DataFrame([val])
	tm.assert_frame_equal(result, expected)
	@skip_pyarrow # CSV parse error: Empty CSV file or block
	@pytest.mark.parametrize(
	"val", [np.iinfo(np.uint64).max + 1, np.iinfo(np.int64).min - 1]
	)
	def test_outside_int64_uint64_range_follow_str(all_parsers, val):
	parser = all_parsers
	result = parser.read_csv(StringIO(f"{val}\nabc"), header=None)
	expected = DataFrame([str(val), "abc"])
	tm.assert_frame_equal(result, expected)