def check_reader(fname):
if not "http:" in fname:
for d in reader(fname):
assert all((k in d for k in "abc"))
assert d['a']
else:
for d in reader(fname):
assert all((k in d for k in "SXEM"))
def check_reader(fname):
if not "http:" in fname:
for d in reader(fname):
assert all((k in d for k in "abc"))
assert d['a']
else:
for d in reader(fname):
assert all((k in d for k in "SXEM"))
def test_split_regex():
fh = open('tt.tmp', 'w')
fh.write("asdf123abc\n")
fh.close()
toks = next(reader('tt.tmp', header=None, sep="\d+"))
assert toks == ['asdf', 'abc'], toks
os.unlink('tt.tmp')
def test_split_None():
with open('tt.tmp', 'w') as fh:
fh.write("asdf 123\tabc\n")
fh.flush()
toks = next(reader('tt.tmp', header=None, sep=None))
assert toks == ['asdf', '123', 'abc'], toks
os.unlink('tt.tmp')
def check_ordered_reader(fname):
if not "http:" in fname:
for d in reader(fname, header="ordered"):
assert all((k in d for k in "abc"))
d["0"] = "extra"
d["_"] = "other"
assert list(d.keys()) == ["a", "b", "c", "0", "_"]
def test_split_regex():
fh = open('tt.tmp', 'w')
fh.write("asdf123abc\n")
fh.close()
toks = next(reader('tt.tmp', header=None, sep="\d+"))
assert toks == ['asdf', 'abc'], toks
os.unlink('tt.tmp')
def test_split_None():
with open('tt.tmp', 'w') as fh:
fh.write("asdf 123\tabc\n")
fh.flush()
toks = next(reader('tt.tmp', header=None, sep=None))
assert toks == ['asdf', '123', 'abc'], toks
os.unlink('tt.tmp')
def check_ordered_reader(fname):
if not "http:" in fname:
for d in reader(fname, header="ordered"):
assert all((k in d for k in "abc"))
d["0"] = "extra"
d["_"] = "other"
assert list(d.keys()) == ["a", "b", "c", "0", "_"]
def test_skip_until():
with open('tta.tmp', 'w') as fh:
fh.write("""#a\n#b\n#c\na\tb\n""")
fiter = reader('tta.tmp', header=False, sep="\t",
skip_while=lambda toks: toks[0].startswith("#"))
f = list(fiter)
assert len(f) == 1, f
assert f[0] == ["a", "b"], f
def test_callable_header():
class Bed(object):
def __init__(self, toks):
self.chrom = toks[0]
self.start = int(toks[1])
self.end = int(toks[2])
fh = nopen(op.join(DATA, "file_data.txt"))
fh.readline() # drop header.
for bed in reader(fh, header=Bed):
assert bed.chrom
assert isinstance(bed.start, int)
def test_skip_until():
with open('tta.tmp', 'w') as fh:
fh.write("""#a\n#b\n#c\na\tb\n""")
fiter = reader('tta.tmp',
header=False,
sep="\t",
skip_while=lambda toks: toks[0].startswith("#"))
f = list(fiter)
assert len(f) == 1, f
assert f[0] == ["a", "b"], f
def test_callable_header():
class Bed(object):
def __init__(self, toks):
self.chrom = toks[0]
self.start = int(toks[1])
self.end = int(toks[2])
fh = nopen(op.join(DATA, "file_data.txt"))
fh.readline() # drop header.
for bed in reader(fh, header=Bed):
assert bed.chrom
assert isinstance(bed.start, int)
def test_namedtuple_header():
from collections import namedtuple
for d in reader(op.join(DATA, "file_data.txt"), header=namedtuple):
assert hasattr(d, "a"), d
assert hasattr(d, "b")
assert hasattr(d, "c")
def check_reader_no_header(fname):
for l in reader(fname, header=False):
assert isinstance(l, list), (l, type(l), fname)
def test_reader_generator():
"""check that reader can accept a generator"""
r = reader(op.join(DATA, "file_data.txt"), header=False)
header = next(r)
for d in reader(r, header=header):
assert all(l in d for l in "abc")
def check_reader_no_header(fname):
for l in reader(fname, header=False):
assert isinstance(l, list), (l, type(l), fname)
def test_reader_generator():
"""check that reader can accept a generator"""
r = reader(op.join(DATA, "file_data.txt"), header=False)
header = next(r)
for d in reader(r, header=header):
assert all(l in d for l in "abc")
def test_namedtuple_header():
from collections import namedtuple
for d in reader(op.join(DATA, "file_data.txt"), header=namedtuple):
assert hasattr(d, "a"), d
assert hasattr(d, "b")
assert hasattr(d, "c")
