def test_upload(runner):
source = os.path.join(testWD,"data","test_reads_R1.fastq.gz")
cmd = f"-b {bucket} -c {credentials_path} upload {source} -o {f1target} -m /tmp/{metadata_name} --silent"
log.debug(cmd)
res = runner.invoke(root, cmd.split())
assert res.exit_code == 0
def verify_fq_suffix(fn):
"""Makes sure the provided file looks like a fastq"""
#Check suffix
if not fn.endswith(("fastq.gz","fq.gz","fastq","fq")):
raise Exception(f"File {fn} is not a fastq")
log.debug(f'Verified that {fn} is a zipped fastq')
#Check for unresolved symlink
if os.path.islink(fn):
if not os.path.exists(os.readlink(fn)):
raise Exception(f"File {fn} is an unresolved symlink")
def read_credentials(credentials_path):
"""Set endpoint, aws id and aws key using a json-file"""
with open(credentials_path, 'r') as inp:
c = json.load(inp)
ep = c['endpoint']
aid = c['aws_access_key_id']
key = c['aws_secret_access_key']
log.debug("Credentials file successfully utilized")
if not all([c['endpoint'], c['aws_access_key_id'], c['aws_secret_access_key']]):
raise MissingCredentialsError('One or more values missing from provided json.')
return [ep,aid,key]
def test_upload_no_destination(runner):
source = os.path.join(testWD,"data","test_reads_R1.fastq.gz")
code_cnt = 0
dest = os.path.basename(source)
cmd = f"-b {bucket} -c {credentials_path} upload {source} -m /tmp/{metadata_name} --silent"
log.debug(cmd)
res = runner.invoke(root, cmd.split())
code_cnt = code_cnt + res.exit_code
cmd1 = f"-b {bucket} -c {credentials_path} delete {dest} -f"
res1 = runner.invoke(root, cmd1.split())
cmd2 = f"-b {bucket} -c {credentials_path} delete {metadata_name} -f"
res2 = runner.invoke(root, cmd2.split())
code_cnt = code_cnt + res1.exit_code
code_cnt = code_cnt + res2.exit_code
assert code_cnt == 0
def generate_tagmap(fn, tag, output_path="{}/meta-{}.json".format(os.getcwd(), TIMESTAMP)):
"""Creates a json file with filenames and tags"""
# Check if meta exists, else make it
if not os.path.exists(output_path):
data = {fn: {'tag': tag}}
with open(output_path, 'w') as out:
json.dump(data, out, indent=4)
else:
# Read the current meta
with open(output_path, 'r') as inp:
current_data = json.load(inp)
# New data
new_data = {fn: {'tag': tag}}
updated_data = {**current_data, **new_data}
# Write updated
with open(output_path, 'w') as out:
json.dump(updated_data, out, indent=4)
log.debug(f'Generated metadata file {output_path}')
def verify_fq_content(fn):
"""Makes sure fastq file contains fastq data"""
nuc = set("ATCGN\n")
lineno = 0
f1 = gzip.open(fn, "r")
for line in f1:
line = line.decode('UTF-8')
lineno = lineno + 1
if lineno == 1:
corr = re.match("^@",line)
elif lineno == 2:
corr = set(line) <= nuc
elif lineno == 3:
corr = re.match("^\+",line)
elif lineno == 4:
lineno = 0
if not corr:
raise Exception(f"File{fn} does not look like a fastq at line {lineno}: {line}")
f1.close()
if lineno % 4 != 0:
raise Exception(f"File {fn} is missing data")
log.debug(f'Verified that {fn} resembles a fastq')
def test_download(runner):
dest = os.path.join('tmp','tst.fq')
cmd = f"-b {bucket} -c {credentials_path} download -f {f1target} -o /{dest} --silent"
log.debug(cmd)
res = runner.invoke(root, cmd.split())
assert res.exit_code == 0