def test_make_modified_TarInfo_when_one_dir_and_no_files(self):
# setup
archive = self.create_tar_archive([('/i/am/a/dir/', tarfile.DIRTYPE)])
# excercise
modified_info = align.make_modified_TarInfo(archive)
# verify
self.assertEqual(modified_info, [])
def main(args):
remove_bam_from_end_re = re.compile("\.bam$")
bam_root = remove_bam_from_end_re.sub("", os.path.basename(args.anno_bam))
with tarfile.open(args.rsem_index, "r:gz") as archive:
archive.extractall(".",
members=make_modified_TarInfo(
archive, "rsem_index"))
rsem_call = shlex.split(
RSEM_COMMAND.format(
rnd_seed=args.rnd_seed,
ncpus=args.ncpus,
ramGB=args.ramGB,
fwd_prob=strand_to_fwd_prob(args.read_strand),
paired_end=format_endedness(args.endedness),
anno_bam=args.anno_bam,
bam_root=bam_root,
))
logger.info("Running RSEM command %s", " ".join(rsem_call))
subprocess.call(rsem_call)
gene_quant_fn = str(bam_root) + "_rsem.genes.results"
number_of_genes_detected = calculate_number_of_genes_detected(
gene_quant_fn)
number_of_genes_detected_dict = {
"number_of_genes_detected": number_of_genes_detected
}
qc_record = QCMetricRecord()
number_of_genes_QC = QCMetric("number_of_genes_detected",
number_of_genes_detected_dict)
qc_record.add(number_of_genes_QC)
with open(str(bam_root) + "_number_of_genes_detected.json", "w") as f:
json.dump(qc_record.to_ordered_dict(), f)
def test_make_modified_TarInfo_with_one_file_and_empty_target_dir(self):
# setup
archive = self.create_tar_archive([('/i/am/a/file.txt',
tarfile.REGTYPE)])
# excercise
modified_info = align.make_modified_TarInfo(archive)
# verify
self.assertEqual(modified_info[0].name, 'file.txt')
def test_make_modified_TarInfo_when_filepath_changes_to_nonempty(self):
# setup
archive = self.create_tar_archive([('/my/old/path/file.txt',
tarfile.REGTYPE)])
# excercise
modified_info = align.make_modified_TarInfo(archive,
target_dir='/my/new/path/')
# verify
self.assertEqual(modified_info[0].name, '/my/new/path/file.txt')
def test_make_modified_TarInfo_with_one_file_one_dir_and_empty_target_dir(
self):
# setup
archive = self.create_tar_archive([("/i/am/a/dir/", tarfile.DIRTYPE),
("/i/am/a/file.txt",
tarfile.REGTYPE)])
# excercise
modified_info = align.make_modified_TarInfo(archive)
# verify
self.assertEqual(len(modified_info), 1)
self.assertEqual(modified_info[0].name, "file.txt")
def main(args):
remove_bam_from_end_re = re.compile('\.bam$')
bam_root = remove_bam_from_end_re.sub('', os.path.basename(args.anno_bam))
with tarfile.open(args.rsem_index, 'r:gz') as archive:
archive.extractall('.',
members=make_modified_TarInfo(
archive, 'rsem_index'))
rsem_call = shlex.split(
RSEM_COMMAND.format(rnd_seed=args.rnd_seed,
ncpus=args.ncpus,
ramGB=args.ramGB,
fwd_prob=strand_to_fwd_prob(args.read_strand),
paired_end=format_endedness(args.endedness),
anno_bam=args.anno_bam,
bam_root=bam_root))
subprocess.call(rsem_call)