def _update_msa(mkfile):
msa = mkfile["MultipleSequenceAlignment"]
defaults = msa.pop("Defaults")
defaults.setdefault("Program", "MAFFT")
defaults["MAFFT"].setdefault("Algorithm", "MAFFT")
for key in mkfile["Project"]["Regions"]:
msa[key] = fill_dict(msa.get(key, {}), defaults)
unknown_regions = set(msa) - set(mkfile["Project"]["Regions"])
if unknown_regions:
raise MakefileError("Unknown Regions of Interest in Genotyping: %s" \
% (", ".join(unknown_regions),))
def _update_msa(mkfile):
msa = mkfile["MultipleSequenceAlignment"]
defaults = msa.pop("Defaults")
defaults.setdefault("Program", "MAFFT")
defaults["MAFFT"].setdefault("Algorithm", "MAFFT")
for key in mkfile["Project"]["Regions"]:
msa[key] = fill_dict(msa.get(key, {}), defaults)
unknown_regions = set(msa) - set(mkfile["Project"]["Regions"])
if unknown_regions:
raise MakefileError("Unknown Regions of Interest in Genotyping: %s" \
% (", ".join(unknown_regions),))
def _do_update_options(options, data, path):
options = copy.deepcopy(options)
if "Options" in data:
if "Features" in data["Options"]:
raise MakefileError("Features may only be specified at root "
"level, not at %r" % (" :: ".join(path), ))
# Fill out missing values using those of prior levels
options = fill_dict(destination=data.pop("Options"),
source=options)
if len(path) < 3:
for key in data:
if key != "Options":
_do_update_options(options, data[key], path + (key, ))
else:
data["Options"] = options
def _update_genotyping(mkfile):
genotyping = mkfile["Genotyping"]
defaults = genotyping.pop("Defaults")
defaults.setdefault("Padding", 5)
defaults["VCF_Filter"].setdefault("MaxReadDepth", 0)
for (key, subdd) in genotyping.items():
if subdd.get("GenotypeEntirePrefix"):
message = ("GenotypeEntirePrefix is only allowed for prefixes "
"using default parameters, but is set for %r" % (key, ))
raise MakefileError(message)
for key in mkfile["Project"]["Regions"]:
genotyping[key] = fill_dict(genotyping.get(key, {}), defaults)
regions = set(genotyping)
unknown_regions = regions - set(mkfile["Project"]["Regions"])
if unknown_regions:
raise MakefileError("Unknown Regions of Interest in Genotyping: %s" %
(", ".join(unknown_regions), ))
def _do_update_options(options, data, path):
options = copy.deepcopy(options)
if "Options" in data:
if "Features" in data["Options"]:
raise MakefileError("Features may only be specified at root "
"level, not at %r" % (" :: ".join(path), ))
# Fill out missing values using those of prior levels
options = fill_dict(destination=data.pop("Options"),
source=options)
# Force feature if 'RescaleQualities' is set, see _mangle_features
if options.pop('RescaleQualities', None):
options['Features']['mapDamage'] = 'rescale'
if len(path) < 2:
for key in data:
if key != "Options":
_do_update_options(options, data[key], path + (key, ))
else:
data["Options"] = options
def _do_update_options(options, data, path):
options = copy.deepcopy(options)
if "Options" in data:
if "Features" in data["Options"]:
raise MakefileError("Features may only be specified at root "
"level, not at %r" % (" :: ".join(path),))
# Fill out missing values using those of prior levels
options = fill_dict(destination=data.pop("Options"),
source=options)
# Force feature if 'RescaleQualities' is set, see _mangle_features
if options.pop('RescaleQualities', None):
options['Features']['mapDamage'] = 'rescale'
if len(path) < 2:
for key in data:
if key != "Options":
_do_update_options(options, data[key], path + (key,))
else:
data["Options"] = options
def _update_genotyping(mkfile):
genotyping = mkfile["Genotyping"]
defaults = genotyping.pop("Defaults")
defaults.setdefault("Padding", 5)
defaults["VCF_Filter"].setdefault("MaxReadDepth", 0)
for (key, subdd) in genotyping.iteritems():
if subdd.get("GenotypeEntirePrefix"):
message = "GenotypeEntirePrefix is only allowed for prefixes " \
"using default parameters, but is set for %r" % (key,)
raise MakefileError(message)
for key in mkfile["Project"]["Regions"]:
subdd = fill_dict(genotyping.get(key, {}), defaults)
subdd["Random"]["--padding"] = subdd["Padding"]
genotyping[key] = subdd
regions = set(genotyping)
unknown_regions = regions - set(mkfile["Project"]["Regions"])
if unknown_regions:
raise MakefileError("Unknown Regions of Interest in Genotyping: %s" \
% (", ".join(unknown_regions),))
def test_fill_dict__source_not_modified():
expected = {"a": 1, "b": {"c": 2, "d": 3}}
source = {"a": 1, "b": {"c": 2, "d": 3}}
destination = {"b": {"d": 0}}
utils.fill_dict(destination, source)
assert_equal(source, expected)
def test_fill_dict__destination_not_modified():
source = {"a": 1, "b": {"c": 2, "d": 3}}
destination = {"b": {"d": 0}}
utils.fill_dict(destination, source)
assert_equal(destination, {"b": {"d": 0}})
def test_fill_dict__filling_full_dict():
source = {"a": 1, "b": {"c": 2, "d": 3}}
destination = {"a": 2, "b": {"c": 3, "d": 4}}
expected = {"a": 2, "b": {"c": 3, "d": 4}}
result = utils.fill_dict(destination, source)
assert_equal(result, expected)
def test_fill_dict__filling_empty_dict():
source = {"a": 1, "b": {"c": 2, "d": 3}}
expected = {"a": 1, "b": {"c": 2, "d": 3}}
result = utils.fill_dict({}, source)
assert_equal(result, expected)
def test_fill_dict__empty_dicts():
result = utils.fill_dict({}, {})
assert_equal(result, {})
def test_fill_dict__source_must_be_dict():
with pytest.raises(TypeError):
utils.fill_dict({}, [])
def test_fill_dict__destination_must_be_dict():
with pytest.raises(TypeError):
utils.fill_dict([], {})
def test_fill_dict__empty_dicts():
result = utils.fill_dict({}, {})
assert result == {}