Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fairly significant changes to check_protocol_fields #531

Merged
merged 2 commits into from
Mar 12, 2024
Merged

Fairly significant changes to check_protocol_fields #531

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e95a8de
Fairly significant changes to check_protocol_fields
ptth222 Feb 5, 2024
733b74f
Missed a small change.
ptth222 Feb 5, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
61 changes: 25 additions & 36 deletions isatools/isatab/validate/rules/rules_40xx.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -254,30 +254,22 @@ def pairwise(iterable):
a, b = tee(iterable)
next(b, None)
return zip(a, b)

proto_ref_index = [i for i in table.columns if 'protocol ref' in i.lower()]
result = True
for each in proto_ref_index:
prots_found = set()
for cell in table[each]:
prots_found.add(cell)
if len(prots_found) > 1:
log.warning("(W) Multiple protocol references {} are found in {}".format(prots_found, each))
log.warning("(W) Only one protocol reference should be used in a Protocol REF column.")
result = False
if result:
field_headers = [i for i in table.columns
if i.lower().endswith(' name')
or i.lower().endswith(' data file')
or i.lower().endswith(' data matrix file')]
protos = [i for i in table.columns if i.lower() == 'protocol ref']
if len(protos) > 0:
last_proto_index = table.columns.get_loc(protos[len(protos) - 1])
else:
last_proto_index = -1
last_mat_or_dat_index = table.columns.get_loc(field_headers[len(field_headers) - 1])
if last_proto_index > last_mat_or_dat_index:
log.warning("(W) Protocol REF column without output in file '" + table.filename + "'")

field_headers = [i for i in table.columns
if i.lower().endswith(' name')
or i.lower().endswith(' data file')
or i.lower().endswith(' data matrix file')]
protos = [i for i in table.columns if i.lower() == 'protocol ref']
if len(protos) > 0:
last_proto_index = table.columns.get_loc(protos[len(protos) - 1])
else:
last_proto_index = -1
last_mat_or_dat_index = table.columns.get_loc(field_headers[len(field_headers) - 1])
if last_proto_index > last_mat_or_dat_index:
spl = "(W) Protocol REF column is not followed by a material or data node in file '" + table.filename + "'"
validator.add_warning(message="Missing Protocol Value", supplemental=spl, code=1007)
log.warning(spl)
if cfg.get_isatab_configuration():
for left, right in pairwise(field_headers):
cleft = None
cright = None
Expand All @@ -294,25 +286,22 @@ def pairwise(iterable):
fprotos_headers = [i for i in raw_headers if 'protocol ref' in i.lower()]
fprotos = list()
for header in fprotos_headers:
proto_name = table.iloc[0][header]
try:
proto_type = proto_map[proto_name]
fprotos.append(proto_type)
except KeyError:
spl = ("Could not find protocol type for protocol name '{}', trying to validate_rules against name "
"only").format(proto_name)
validator.add_warning(message="Missing Protocol declaration", supplemental=spl, code=1007)
log.warning("(W) {}".format(spl))
fprotos.append(proto_name)
proto_names = list(table.loc[:, header].unique())
for proto_name in proto_names:
proto_type = proto_map.get(proto_name)
if not proto_type and proto_name:
spl = ("Could not find protocol type for protocol name '{}' in file '{}'" ).format(proto_name, table.filename)
validator.add_warning(message="Missing Protocol Declaration", supplemental=spl, code=1007)
log.warning("(W) {}".format(spl))
else:
fprotos.append(proto_type)
invalid_protos = set(cprotos) - set(fprotos)
if len(invalid_protos) > 0:
spl = ("Protocol(s) of type {} defined in the ISA-configuration expected as a between '{}' and "
"'{}' but has not been found, in the file '{}'")
spl = spl.format(str(list(invalid_protos)), cleft.header, cright.header, table.filename)
validator.add_warning(message="Missing Protocol declaration", supplemental=spl, code=1007)
log.warning("(W) {}".format(spl))
result = False
return result


def load_table_checks(df, filename):
Expand Down
Loading