def test_file_handle(self):
try:
f = open(self.csv1, 'rb')
reader = TextReader(f)
result = reader.read() # noqa
finally:
f.close()
def test_file_handle_mmap(self):
try:
f = open(self.csv1, 'rb')
reader = TextReader(f, memory_map=True, header=None)
reader.read()
finally:
f.close()
def test_parse_booleans(self):
data = 'True\nFalse\nTrue\nTrue'
reader = TextReader(StringIO(data), header=None)
result = reader.read()
assert result[0].dtype == np.bool_
def test_embedded_newline(self):
data = 'a\n"hello\nthere"\nthis'
reader = TextReader(StringIO(data), header=None)
result = reader.read()
expected = np.array(['a', 'hello\nthere', 'this'], dtype=np.object_)
tm.assert_numpy_array_equal(result[0], expected)
def test_integer_thousands(self):
data = '123,456\n12,500'
reader = TextReader(StringIO(data), delimiter=':',
thousands=',', header=None)
result = reader.read()
expected = np.array([123456, 12500], dtype=np.int64)
tm.assert_almost_equal(result[0], expected)
def test_euro_decimal(self):
data = '12345,67\n345,678'
reader = TextReader(StringIO(data), delimiter=':',
decimal=',', header=None)
result = reader.read()
expected = np.array([12345.67, 345.678])
tm.assert_almost_equal(result[0], expected)
def test_escapechar(self):
data = ('\\"hello world\"\n'
'\\"hello world\"\n'
'\\"hello world\"')
reader = TextReader(StringIO(data), delimiter=',', header=None,
escapechar='\\')
result = reader.read()
expected = {0: np.array(['"hello world"'] * 3, dtype=object)}
assert_array_dicts_equal(result, expected)
def test_delimit_whitespace(self):
data = 'a b\na\t\t "b"\n"a"\t \t b'
reader = TextReader(StringIO(data), delim_whitespace=True,
header=None)
result = reader.read()
tm.assert_numpy_array_equal(result[0], np.array(['a', 'a', 'a'],
dtype=np.object_))
tm.assert_numpy_array_equal(result[1], np.array(['b', 'b', 'b'],
dtype=np.object_))
def test_skipinitialspace(self):
data = ('a, b\n'
'a, b\n'
'a, b\n'
'a, b')
reader = TextReader(StringIO(data), skipinitialspace=True,
header=None)
result = reader.read()
tm.assert_numpy_array_equal(result[0], np.array(['a', 'a', 'a', 'a'],
dtype=np.object_))
tm.assert_numpy_array_equal(result[1], np.array(['b', 'b', 'b', 'b'],
dtype=np.object_))
def _make_reader(**kwds):
if "dtype" in kwds:
kwds["dtype"] = ensure_dtype_objs(kwds["dtype"])
return TextReader(StringIO(data),
delimiter=",",
header=None,
**kwds)
def test_empty_field_eof(self):
data = 'a,b,c\n1,2,3\n4,,'
result = TextReader(StringIO(data), delimiter=',').read()
expected = {0: np.array([1, 4], dtype=np.int64),
1: np.array(['2', ''], dtype=object),
2: np.array(['3', ''], dtype=object)}
assert_array_dicts_equal(result, expected)
# GH5664
a = DataFrame([['b'], [nan]], columns=['a'], index=['a', 'c'])
b = DataFrame([[1, 1, 1, 0], [1, 1, 1, 0]],
columns=list('abcd'),
index=[1, 1])
c = DataFrame([[1, 2, 3, 4], [6, nan, nan, nan],
[8, 9, 10, 11], [13, 14, nan, nan]],
columns=list('abcd'),
index=[0, 5, 7, 12])
for _ in range(100):
df = read_csv(StringIO('a,b\nc\n'), skiprows=0,
names=['a'], engine='c')
assert_frame_equal(df, a)
df = read_csv(StringIO('1,1,1,1,0\n' * 2 + '\n' * 2),
names=list("abcd"), engine='c')
assert_frame_equal(df, b)
df = read_csv(StringIO('0,1,2,3,4\n5,6\n7,8,9,10,11\n12,13,14'),
names=list('abcd'), engine='c')
assert_frame_equal(df, c)
def test_header_not_enough_lines(self):
data = ('skip this\n'
'skip this\n'
'a,b,c\n'
'1,2,3\n'
'4,5,6')
reader = TextReader(StringIO(data), delimiter=',', header=2)
header = reader.header
expected = [['a', 'b', 'c']]
assert header == expected
recs = reader.read()
expected = {0: np.array([1, 4], dtype=np.int64),
1: np.array([2, 5], dtype=np.int64),
2: np.array([3, 6], dtype=np.int64)}
assert_array_dicts_equal(recs, expected)
def test_header_not_enough_lines(self):
data = ('skip this\n' 'skip this\n' 'a,b,c\n' '1,2,3\n' '4,5,6')
reader = TextReader(StringIO(data), delimiter=',', header=2)
header = reader.header
expected = [['a', 'b', 'c']]
assert header == expected
recs = reader.read()
expected = {0: [1, 4], 1: [2, 5], 2: [3, 6]}
assert_array_dicts_equal(expected, recs)
# not enough rows
pytest.raises(parser.ParserError,
TextReader,
StringIO(data),
delimiter=',',
header=5,
as_recarray=True)
def test_header_not_enough_lines(self):
data = ('skip this\n'
'skip this\n'
'a,b,c\n'
'1,2,3\n'
'4,5,6')
reader = TextReader(StringIO(data), delimiter=',', header=2)
header = reader.header
expected = [['a', 'b', 'c']]
assert header == expected
recs = reader.read()
expected = {0: [1, 4], 1: [2, 5], 2: [3, 6]}
assert_array_dicts_equal(expected, recs)
# not enough rows
pytest.raises(parser.ParserError, TextReader, StringIO(data),
delimiter=',', header=5, as_recarray=True)
def test_skip_bad_lines(self):
# too many lines, see #2430 for why
data = ('a:b:c\n'
'd:e:f\n'
'g:h:i\n'
'j:k:l:m\n'
'l:m:n\n'
'o:p:q:r')
reader = TextReader(StringIO(data), delimiter=':',
header=None)
pytest.raises(parser.ParserError, reader.read)
reader = TextReader(StringIO(data), delimiter=':',
header=None,
error_bad_lines=False,
warn_bad_lines=False)
result = reader.read()
expected = {0: ['a', 'd', 'g', 'l'],
1: ['b', 'e', 'h', 'm'],
2: ['c', 'f', 'i', 'n']}
assert_array_dicts_equal(result, expected)
reader = TextReader(StringIO(data), delimiter=':',
header=None,
error_bad_lines=False,
warn_bad_lines=True)
reader.read()
val = sys.stderr.getvalue()
assert 'Skipping line 4' in val
assert 'Skipping line 6' in val
def test_empty_field_eof(self):
data = "a,b,c\n1,2,3\n4,,"
result = TextReader(StringIO(data), delimiter=",").read()
expected = {
0: np.array([1, 4], dtype=np.int64),
1: np.array(["2", ""], dtype=object),
2: np.array(["3", ""], dtype=object),
}
assert_array_dicts_equal(result, expected)
# GH5664
a = DataFrame([["b"], [np.nan]], columns=["a"], index=["a", "c"])
b = DataFrame([[1, 1, 1, 0], [1, 1, 1, 0]],
columns=list("abcd"),
index=[1, 1])
c = DataFrame(
[
[1, 2, 3, 4],
[6, np.nan, np.nan, np.nan],
[8, 9, 10, 11],
[13, 14, np.nan, np.nan],
],
columns=list("abcd"),
index=[0, 5, 7, 12],
)
for _ in range(100):
df = read_csv(StringIO("a,b\nc\n"),
skiprows=0,
names=["a"],
engine="c")
tm.assert_frame_equal(df, a)
df = read_csv(StringIO("1,1,1,1,0\n" * 2 + "\n" * 2),
names=list("abcd"),
engine="c")
tm.assert_frame_equal(df, b)
df = read_csv(
StringIO("0,1,2,3,4\n5,6\n7,8,9,10,11\n12,13,14"),
names=list("abcd"),
engine="c",
)
tm.assert_frame_equal(df, c)
def test_cr_delimited(self, text, kwargs):
nice_text = text.replace("\r", "\r\n")
result = TextReader(StringIO(text), **kwargs).read()
expected = TextReader(StringIO(nice_text), **kwargs).read()
assert_array_dicts_equal(result, expected)
def test_StringIO(self, csv_path):
with open(csv_path, "rb") as f:
text = f.read()
src = BytesIO(text)
reader = TextReader(src, header=None)
reader.read()
def test_file_handle_mmap(self):
# this was never using memory_map=True
with open(self.csv1, "rb") as f:
reader = TextReader(f, header=None)
reader.read()
def test_StringIO(self):
with open(self.csv1, 'rb') as f:
text = f.read()
src = BytesIO(text)
reader = TextReader(src, header=None)
reader.read()
def test_string_filename(self):
reader = TextReader(self.csv1, header=None)
reader.read()
def _test(text, **kwargs):
nice_text = text.replace('\r', '\r\n')
result = TextReader(StringIO(text), **kwargs).read()
expected = TextReader(StringIO(nice_text), **kwargs).read()
assert_array_dicts_equal(result, expected)
def test_file_handle(self):
with open(self.csv1, 'rb') as f:
reader = TextReader(f)
reader.read()
def test_skip_bad_lines(self, capsys):
# too many lines, see #2430 for why
data = ('a:b:c\n'
'd:e:f\n'
'g:h:i\n'
'j:k:l:m\n'
'l:m:n\n'
'o:p:q:r')
reader = TextReader(StringIO(data), delimiter=':',
header=None)
msg = (r"Error tokenizing data\. C error: Expected 3 fields in"
" line 4, saw 4")
with pytest.raises(parser.ParserError, match=msg):
reader.read()
reader = TextReader(StringIO(data), delimiter=':',
header=None,
error_bad_lines=False,
warn_bad_lines=False)
result = reader.read()
expected = {0: np.array(['a', 'd', 'g', 'l'], dtype=object),
1: np.array(['b', 'e', 'h', 'm'], dtype=object),
2: np.array(['c', 'f', 'i', 'n'], dtype=object)}
assert_array_dicts_equal(result, expected)
reader = TextReader(StringIO(data), delimiter=':',
header=None,
error_bad_lines=False,
warn_bad_lines=True)
reader.read()
captured = capsys.readouterr()
assert 'Skipping line 4' in captured.err
assert 'Skipping line 6' in captured.err
def _make_reader(**kwds):
return TextReader(StringIO(data),
delimiter=",",
header=None,
**kwds)
def test_skip_bad_lines(self, capsys):
# too many lines, see #2430 for why
data = "a:b:c\nd:e:f\ng:h:i\nj:k:l:m\nl:m:n\no:p:q:r"
reader = TextReader(StringIO(data), delimiter=":", header=None)
msg = r"Error tokenizing data\. C error: Expected 3 fields in line 4, saw 4"
with pytest.raises(parser.ParserError, match=msg):
reader.read()
reader = TextReader(
StringIO(data),
delimiter=":",
header=None,
error_bad_lines=False,
warn_bad_lines=False,
)
result = reader.read()
expected = {
0: np.array(["a", "d", "g", "l"], dtype=object),
1: np.array(["b", "e", "h", "m"], dtype=object),
2: np.array(["c", "f", "i", "n"], dtype=object),
}
assert_array_dicts_equal(result, expected)
reader = TextReader(
StringIO(data),
delimiter=":",
header=None,
error_bad_lines=False,
warn_bad_lines=True,
)
reader.read()
captured = capsys.readouterr()
assert "Skipping line 4" in captured.err
assert "Skipping line 6" in captured.err
def test_file_handle(self, csv_path):
with open(csv_path, "rb") as f:
reader = TextReader(f)
reader.read()
def _make_reader(**kwds):
return TextReader(StringIO(data), delimiter=',', **kwds)
def test_string_filename(self):
reader = TextReader(self.csv1, header=None)
reader.read()
def test_file_handle(self):
with open(self.csv1, 'rb') as f:
reader = TextReader(f)
reader.read()
def test_file_handle_mmap(self):
with open(self.csv1, 'rb') as f:
reader = TextReader(f, memory_map=True, header=None)
reader.read()
def test_file_handle_mmap(self):
with open(self.csv1, 'rb') as f:
reader = TextReader(f, memory_map=True, header=None)
reader.read()
def test_StringIO(self):
with open(self.csv1, 'rb') as f:
text = f.read()
src = BytesIO(text)
reader = TextReader(src, header=None)
reader.read()
def test_string_factorize(self):
# should this be optional?
data = 'a\nb\na\nb\na'
reader = TextReader(StringIO(data), header=None)
result = reader.read()
assert len(set(map(id, result[0]))) == 2
def test_string_factorize(self):
# should this be optional?
data = 'a\nb\na\nb\na'
reader = TextReader(StringIO(data), header=None)
result = reader.read()
assert len(set(map(id, result[0]))) == 2
