def _world_from_cwl(fnargs, work_dir):
"""Reconstitute a bcbio world data object from flattened CWL-compatible inputs.
Converts the flat CWL representation into a nested bcbio world dictionary.
Handles single sample inputs (returning a single world object) and multi-sample
runs (returning a list of individual samples to get processed together).
"""
parallel = None
output_cwl_keys = None
runtime = {}
out = []
data = {}
passed_keys = []
for fnarg in fnargs:
key, val = fnarg.split("=")
# extra values pulling in nested indexes
if key == "ignore":
continue
if key == "sentinel-parallel":
parallel = val
continue
if key == "sentinel-runtime":
runtime = json.loads(val)
continue
if key == "sentinel-outputs":
output_cwl_keys = json.loads(val)
continue
# starting a new record -- duplicated key
if key in passed_keys:
data["dirs"] = {"work": work_dir}
data["cwl_keys"] = passed_keys
data["output_cwl_keys"] = output_cwl_keys
data = _add_resources(data, runtime)
data = run_info.normalize_world(data)
out.append(data)
data = {}
passed_keys = []
passed_keys.append(key)
key = key.split("__")
if val.startswith(("{", "[")):
val = json.loads(val)
elif val.find(";;") >= 0:
val = val.split(";;")
data = _update_nested(key, val, data)
if data:
data["dirs"] = {"work": work_dir}
data["cwl_keys"] = passed_keys
data["output_cwl_keys"] = output_cwl_keys
data = _add_resources(data, runtime)
data = run_info.normalize_world(data)
out.append(data)
if parallel in ["single-parallel", "single-merge", "multi-parallel", "multi-combined", "multi-batch",
"batch-split", "batch-parallel", "batch-merge", "batch-single"]:
out = [out]
else:
assert len(out) == 1, "%s\n%s" % (pprint.pformat(out), pprint.pformat(fnargs))
return out, parallel
def _world_from_cwl(fnargs, work_dir):
"""Reconstitute a bcbio world data object from flattened CWL-compatible inputs.
Converts the flat CWL representation into a nested bcbio world dictionary.
Handles single sample inputs (returning a single world object) and multi-sample
runs (returning a list of individual samples to get processed together).
"""
parallel = None
runtime = {}
out = []
data = {}
passed_keys = []
for fnarg in fnargs:
key, val = fnarg.split("=")
# extra values pulling in nested indexes
if key == "ignore":
continue
if key == "sentinel-parallel":
parallel = val
continue
if key == "sentinel-runtime":
runtime = json.loads(val)
continue
# starting a new record -- duplicated key
if key in passed_keys:
data["dirs"] = {"work": work_dir}
data["cwl_keys"] = passed_keys
data = _add_resources(data, runtime)
data = run_info.normalize_world(data)
out.append(data)
data = {}
passed_keys = []
passed_keys.append(key)
key = key.split("__")
if val.startswith(("{", "[")):
val = json.loads(val)
elif val.find(";;") >= 0:
val = val.split(";;")
data = _update_nested(key, val, data)
if data:
data["dirs"] = {"work": work_dir}
data["cwl_keys"] = passed_keys
data = _add_resources(data, runtime)
data = run_info.normalize_world(data)
out.append(data)
if parallel in ["single-parallel", "single-merge", "multi-parallel", "multi-combined", "multi-batch",
"batch-split", "batch-parallel", "batch-merge", "batch-single"]:
out = [out]
else:
assert len(out) == 1, "%s\n%s" % (pprint.pformat(out), pprint.pformat(fnargs))
return out, parallel
def _world_from_cwl(fnargs, work_dir):
"""Reconstitute a bcbio world data object from flattened CWL-compatible inputs.
Converts the flat CWL representation into a nested bcbio world dictionary.
Handles single sample inputs (returning a single world object) and multi-sample
runs (returning a list of individual samples to get processed together).
"""
multisample = False
out = []
data = {}
passed_keys = []
for fnarg in fnargs:
key, val = fnarg.split("=")
# extra values pulling in nested indexes
if key == "ignore":
continue
if key == "sentinel":
if val == "multisample":
multisample = True
else:
raise ValueError("Unexpected sentinel %s" % fnarg)
continue
# starting a new record -- duplicated key
if key in passed_keys:
data["dirs"] = {"work": work_dir}
# XXX Determine cores and other resources from CWL
data["config"]["resources"] = {}
data = run_info.normalize_world(data)
out.append(data)
data = {}
passed_keys = []
passed_keys.append(key)
key = key.split("__")
if val.startswith(("{", "[")):
val = json.loads(val)
elif val.find(";;") >= 0:
val = val.split(";;")
data = _update_nested(key, val, data)
if data:
data["dirs"] = {"work": work_dir}
# XXX Determine cores and other resources from CWL
data["config"]["resources"] = {}
data = run_info.normalize_world(data)
out.append(data)
if multisample:
out = [out]
else:
assert len(out) == 1, "%s\n%s" % (pprint.pformat(out), pprint.pformat(fnargs))
return out, multisample
def _finalize_cwl_in(data, work_dir, passed_keys, output_cwl_keys, runtime):
"""Finalize data object with inputs from CWL.
"""
data["dirs"] = {"work": work_dir}
if not tz.get_in(["config", "algorithm"], data):
if "config" not in data:
data["config"] = {}
data["config"]["algorithm"] = {}
if "rgnames" not in data and "description" in data:
data["rgnames"] = {"sample": data["description"]}
data["cwl_keys"] = passed_keys
data["output_cwl_keys"] = output_cwl_keys
data = _add_resources(data, runtime)
data = run_info.normalize_world(data)
return data
def _finalize_cwl_in(data, work_dir, passed_keys, output_cwl_keys, runtime):
"""Finalize data object with inputs from CWL.
"""
data["dirs"] = {"work": work_dir}
if not tz.get_in(["config", "algorithm"], data):
if "config" not in data:
data["config"] = {}
data["config"]["algorithm"] = {}
if "rgnames" not in data and "description" in data:
data["rgnames"] = {"sample": data["description"]}
data["cwl_keys"] = passed_keys
data["output_cwl_keys"] = output_cwl_keys
data = _add_resources(data, runtime)
data = run_info.normalize_world(data)
return data
def _world_from_cwl(fnargs, work_dir):
"""Reconstitute a bcbio world data object from flattened CWL-compatible inputs.
Converts the flat CWL representation into a nested bcbio world dictionary.
"""
data = {}
for fnarg in fnargs:
key, val = fnarg.split("=")
key = key.split("__")
if val.startswith(("{", "[")):
val = json.loads(val)
data = tz.update_in(data, key, lambda x: val)
data["dirs"] = {"work": work_dir}
# XXX Determine cores and other resources from CWL
data["config"]["resources"] = {}
data = run_info.normalize_world(data)
return [data]
def _world_from_cwl(fnargs, work_dir):
"""Reconstitute a bcbio world data object from flattened CWL-compatible inputs.
Converts the flat CWL representation into a nested bcbio world dictionary.
"""
data = {}
for fnarg in fnargs:
key, val = fnarg.split("=")
key = key.split("__")
if val.startswith(("{", "[")):
val = json.loads(val)
data = tz.update_in(data, key, lambda x: val)
data["dirs"] = {"work": work_dir}
# XXX Determine cores and other resources from CWL
data["config"]["resources"] = {}
data = run_info.normalize_world(data)
return [data]