def test_merge_records__complex_example__unsorted():
assert merge_bed_records(
[
_new_bed_record("chr2", 100, 200),
_new_bed_record("chr1", 1234, 5678),
_new_bed_record("chr2", 150, 250),
_new_bed_record("chr2", 1, 20),
_new_bed_record("chr1", 5678, 9012),
]
) == [
_new_bed_record("chr1", 1234, 9012),
_new_bed_record("chr2", 1, 20),
_new_bed_record("chr2", 100, 250),
]
def _run(self, config, temp):
contigs = {}
with open(self._fai_file) as handle:
for line in handle:
name, length, _ = line.split("\t", 2)
if name in contigs:
raise NodeError("Reference genome contains multiple "
"identically named contigs (%r)!" %
(name, ))
contigs[name] = int(length)
with open(reroot_path(temp, self._outfile), "w") as handle:
records = list(read_bed_file(self._infile, contigs=contigs))
pad_bed_records(records=records,
padding=self._amount,
max_sizes=contigs)
for record in merge_bed_records(records):
handle.write("%s\n" % (record, ))
def test_merge_records__non_overlapping_records_2():
assert merge_bed_records(
[_new_bed_record("chr1", 1234, 5678), _new_bed_record("chr1", 5680, 9012)]
) == [_new_bed_record("chr1", 1234, 5678), _new_bed_record("chr1", 5680, 9012)]
def test_merge_records__minimal_fields_only():
assert merge_bed_records([_new_bed_record("chr1", 1234, 5678, "foo", 1, "-")]) == [
_new_bed_record("chr1", 1234, 5678)
]
def test_merge_records__single_record():
assert merge_bed_records([_new_bed_record("chr1", 1234, 5678)]) == [
_new_bed_record("chr1", 1234, 5678)
]
def test_merge_records__empty_sequences():
assert merge_bed_records(()) == []
assert merge_bed_records([]) == []
