def __init__(self, term, role, synonyms, tree_position):
Term.__init__(self, term, role, synonyms)
# The tree position must always be a set
if type(tree_position) is not set:
raise TypeError("The tree position must be a set, but I received"
"a %r instead (which is a %r)", tree_position,
type(tree_position))
self.__tree_position=tree_position
def __init__(self, term, role, synonyms, tree_position):
Term.__init__(self, term, role, synonyms)
# The tree position must always be a set
if type(tree_position) is not set:
raise TypeError(
"The tree position must be a set, but I received"
"a %r instead (which is a %r)", tree_position,
type(tree_position))
self.__tree_position = tree_position
def check_for_subheadings(self, an_expression):
"Checks to see if this expression needs a subheading added."
positions = [
self._tree[a_term.term].position
for a_term in an_expression.utterance
]
for position in positions:
for rule in self.data.subheading_rules:
"""Check each position in each tree for membership in the
tree-based checktag rules"""
if 'in' in rule:
in_rule = any(
[any([x in y for x in rule['in']]) for y in position])
else:
in_rule = False
if 'not in' in rule:
not_in_rule = any([
any([x in y for x in rule['not in']]) for y in position
])
else:
not_in_rule = False
if in_rule and not not_in_rule:
logging.log(ULTRADEBUG,
"Expression %r matches subheading rule %r",
an_expression, rule)
return [Term(x) for x in rule['terms']]
return []
def check_extra_checktag_rules(self, an_expression):
"""Checks to see if a mesh term is in a known checktag-emitting
tree"""
positions = [
self._tree[a_term.term].position
for a_term in an_expression.utterance
]
for position in positions:
for rule in self.data.extra_checktag_rules:
"""Check each position in each tree for membership in the
tree-based checktag rules"""
if 'in' in rule:
in_rule = any(
[any([x in y for x in rule['in']]) for y in position])
else:
in_rule = False
if 'not in' in rule:
not_in_rule = any([
any([x in y for x in rule['not in']]) for y in position
])
else:
not_in_rule = False
if in_rule and not not_in_rule:
logging.log(ULTRADEBUG,
"Expression %r matches checktag rule %r",
an_expression, rule)
self._extra_checktags |= set(
[Term(x) for x in rule['terms']])
return
def from_medline(self, medline_string):
"""Reformats a MEDLINE record headings field into an Expression by
splitting across / lowercasing and removing stars. Also assigns the
role of '*' to starred terms."""
self._utterance = [
Term(x, '*' if '*' in x else "")
for x in medline_string.strip().replace('*', "").split('/')
]
self._original_utterance = medline_string
return self # For method chaining
def major_heading(self):
"""Returns a Major Heading if there is one; otherwise, returns
nothing"""
if isinstance(self._original_utterance, list):
potential_terms = self._original_utterance
else:
potential_terms = [
x for x in self._original_utterance.strip().split('/')
]
potential_terms = [
Term(x.replace('*', ''), '*' if '*' in x else "")
for x in potential_terms if '*' in x
]
return potential_terms
def check_checktag_rules(self, CUI):
"""Compares a CUI to the checktag rules, and emits checktags if it
matches. If a CUI is a member of an MTI list, and the list is a known
match to a checktag, we emit the checktag at the end of the
process."""
# We check every list for membership (except exclusions)
for (listname, checktags) in self.data.checktag_rules.iteritems():
if listname == '_exclusions':
continue
if CUI in self.data.lists[listname]:
logging.log(ULTRADEBUG,
'CUI %r matches list %r. Checktags %r added.', CUI,
listname, checktags)
self._extra_checktags |= set([Term(x) for x in checktags])
def convert_step_2(self, umls_concept):
"""Converts a UMLS concept into a MeSH expression."""
if umls_concept.mapping_method not in self._accepted_types:
# Unless there's only a single concept as a target
if len(umls_concept.names_and_ids) == 1:
return Expression(
[Term(x) for x in umls_concept.names_and_ids.itervalues()])
else:
#logging.debug("Concept %r has an unsupported mapping type",
# umls_concept)
return Expression([])
#pass
# Concepts mapped with mapping method "A" are associated expressions,
# i.e. compound mappings
if umls_concept.mapping_method == 'a':
return Expression(
[Term(x) for x in umls_concept.names_and_ids.itervalues()])
# Now only the synonyms remain. Is there just one item? Return it.
if len(umls_concept.names_and_ids) == 1:
return Expression(
[Term(x) for x in umls_concept.names_and_ids.itervalues()])
# Is there just one descriptor? Return it.
descriptors = [
umls_concept.names_and_ids[x]
for x in umls_concept.names_and_ids.iter_descriptors()
]
if len(descriptors) == 1:
return Expression([Term(x) for x in descriptors])
# Is there one descriptor identical to the name? Return the concept
# name.
if len([x for x in descriptors
if x == umls_concept.concept_name]) == 1:
return Expression([Term(umls_concept.concept_name)])
# Do all qualifiers and descriptors share the same text?
qualifiers = [
umls_concept.names_and_ids[x]
for x in umls_concept.names_and_ids.iter_qualifiers()
]
unique_names = set(descriptors) | set(qualifiers)
if len(unique_names) == 1:
# Return the only name
return Expression(Term(unique_names.pop()))
# I give up; return the deepest item according to the tree.
tree_depths = [(self._tree[x].deepest_depth(), x)
for x in umls_concept.names_and_ids.itervalues()]
tree_depths.sort(reverse=True)
deepest = self._tree.deepest_of_list(
x for x in umls_concept.names_and_ids.itervalues())
return Expression([Term(deepest)]) # Return the term
def __setstate__(self, state):
Term.__setstate__(self, state)
self.__tree_position=state['pos']
def __getstate__(self):
tstate=Term.__getstate__(self)
tstate['pos']=self.__tree_position
return tstate
def testBasicConversion(self):
output = self.ruleless_converter.convert(self.buildRankedResultSet())
self.assert_(type(output) is RankedConversionResult)
output = [x for x in output]
self.assertEqual(Term('hareitosis'), output[0][0].utterance[0])
def __getstate__(self):
tstate = Term.__getstate__(self)
tstate['pos'] = self.__tree_position
return tstate
def __setstate__(self, state):
Term.__setstate__(self, state)
self.__tree_position = state['pos']
def convert_step_2(self, umls_concept):
return Expression([Term(x) for x in
umls_concept.names_and_ids.itervalues()])
