def _write_tsv(fname, dictionary, overwrite=False, verbose=False):
"""Write an ordered dictionary to a .tsv file."""
if op.exists(fname) and not overwrite:
raise FileExistsError(f'"{fname}" already exists. '
'Please set overwrite to True.')
_to_tsv(dictionary, fname)
if verbose:
print(os.linesep + f"Writing '{fname}'..." + os.linesep)
print(_tsv_to_str(dictionary))
def _write_tsv(fname, dictionary, overwrite=False, verbose=False):
"""Write an ordered dictionary to a .tsv file."""
if op.exists(fname) and not overwrite:
raise FileExistsError('"%s" already exists. Please set ' # noqa: F821
'overwrite to True.' % fname)
_to_tsv(dictionary, fname)
if verbose:
print(os.linesep + "Writing '%s'..." % fname + os.linesep)
print(_tsv_to_str(dictionary))
def test_tsv_handler(tmp_path):
"""Test the TSV handling."""
# create some dummy data
d = odict(a=[1, 2, 3, 4], b=['five', 'six', 'seven', 'eight'])
assert _contains_row(d, {'a': 1, 'b': 'five'})
d2 = odict(a=[5], b=['nine'])
d = _combine_rows(d, d2)
assert 5 in d['a']
d2 = odict(a=[5])
d = _combine_rows(d, d2)
assert 'n/a' in d['b']
d2 = odict(a=[5], b=['ten'])
d = _combine_rows(d, d2, drop_column='a')
# make sure that the repeated data was dropped
assert 'nine' not in d['b']
print(_tsv_to_str(d))
d_path = tmp_path / 'output.tsv'
# write the data to an output tsv file
_to_tsv(d, d_path)
# now read it back
d = _from_tsv(d_path)
# test reading the file in with the incorrect number of datatypes raises
# an Error
with pytest.raises(ValueError):
d = _from_tsv(d_path, dtypes=[str])
# we can also pass just a single data type and it will be applied to all
# columns
d = _from_tsv(d_path, str)
# remove any rows with 2 or 5 in them
d = _drop(d, [2, 5], 'a')
assert 2 not in d['a']
# test combining data with differing numbers of columns
d = odict(a=[1, 2], b=['three', 'four'])
d2 = odict(a=[4], b=['five'], c=[3.1415])
# raise error if a new column is tried to be added
with pytest.raises(KeyError):
d = _combine_rows(d, d2)
d2 = odict(a=[5])
d = _combine_rows(d, d2)
assert d['b'] == ['three', 'four', 'n/a']
assert _contains_row(d, {'a': 5})
# test reading a single column
_to_tsv(odict(a=[1, 2, 3, 4]), d_path)
d = _from_tsv(d_path)
assert d['a'] == ['1', '2', '3', '4']
