def test_round_trip(self):
test_bam = resource_stream(__name__, 'data/minitest.bam')
# get raw uncompressed content
content = gzip.open(test_bam).read()
# go back to start of file and parse with Filereader
test_bam.seek(0)
the_bam = bam.FileReader(gzip.open(test_bam))
out_file = NamedTemporaryFile(delete=False)
out_file_name = out_file.name
with bam.FileWriter(out_file_name) as out_bam:
out_bam.raw_header = the_bam.raw_header
out_bam.raw_refs = the_bam.raw_refs
out_bam.write_header()
self.assertRaises(RuntimeError,out_bam.write_header,None)
for align in the_bam:
out_bam.write(align)
# parse the new temporary file
new_bam = bam.FileReader(gzip.open(out_file_name))
self.assertEqual(the_bam.header,new_bam.header)
try:
while True:
align = next(the_bam)
align2 = next(the_bam)
self.assertEqual(align,align2)
except StopIteration:
pass
def test_FileReader_init(self):
test_bam = resource_stream(__name__, 'data/paired_end_testdata_human.bam')
the_bam = bam.FileReader(gzip.open(test_bam))
self.assertEqual(the_bam.raw_header, RAW_HEADER)
self.assertEqual(the_bam.raw_refs, RAW_REFS)
self.assertEqual(the_bam.refs, REFS)
self.assertEqual(the_bam.header, HEADER)
self.assertEqual(the_bam.index_to_ref, INDEX_TO_REF)
self.assertEqual(the_bam.ref_to_index, REF_TO_INDEX)
self.assertEqual(the_bam.sort_order, 'unsorted')
the_bam.close()
test_bam = resource_stream(__name__, 'data/paired_end_testdata_human.bam')
with bam.FileReader(gzip.open(test_bam)) as the_bam:
self.assertEqual(the_bam.header, HEADER)
first_read = next(the_bam)
the_bam.reset_alignments()
self.assertEqual(first_read,next(the_bam))
self.assertRaises(ValueError, bam.FileReader, test_bam)
def test_FileReader_iteration(self):
test_bam = resource_stream(__name__, 'data/paired_end_testdata_human.bam')
the_bam = bam.FileReader(gzip.open(test_bam))
self.assertEqual(next(the_bam), ALIGN0)
for i in range(41):
next(the_bam)
self.assertEqual(next(the_bam), ALIGN42)
for align in the_bam:
pass
def test_update_header_length(self):
test_bam = resource_stream(__name__, 'data/paired_end_testdata_human.bam')
the_bam = bam.FileReader(gzip.open(test_bam))
the_bam.raw_header = the_bam.raw_header+b'@CO\tThis is an extra comment\n'
the_bam.update_header_length()
self.assertEqual(len(the_bam.raw_header[4:]),
struct.unpack("<i", the_bam.raw_header[:4])[0])
header_with_incorrect_len = struct.pack("<i",42)+RAW_HEADER[4:]
self.assertEqual(the_bam.update_header_length(header_with_incorrect_len)[:4],
RAW_HEADER[:4])
def test_get_updated_header(self):
test_bam = resource_stream(__name__, 'data/paired_end_testdata_human.bam')
the_bam = bam.FileReader(gzip.open(test_bam))
the_bam.raw_header = the_bam.raw_header+b'@CO\tThis is an extra comment\n'
the_bam.update_header_length()
updated_header = the_bam.get_updated_header(id='test',
program='test',
version='88.88.8',
command="--argumentative")
self.assertEqual(updated_header[4:], #skip 4 bytes as len changed
(RAW_HEADER[4:]
+ b'@PG\tID:test\tPN:test\tVN:88.88.8\tPP:bowtie2\t'
+ b'CL:--argumentative\n'
+ b'@CO\tThis is an extra comment\n')
)