def write_nested_lists(fl): # fl is the absolute *path* to the file which contains the ontology file
try:
n_lists = parse_ontologies.nested_lists(fl)
except:
fl = re.sub('updated', 'original', fl)
print fl
n_lists = parse_ontologies.nested_lists(fl)
f = open(path_to_pa+'updated/nested_lists.py', 'w')
f.write('nlists = '+str(n_lists))
f.close()
def write_nested_lists(
fl
): # fl is the absolute *path* to the file which contains the ontology file
try:
n_lists = parse_ontologies.nested_lists(fl)
except:
fl = re.sub('updated', 'original', fl)
print fl
n_lists = parse_ontologies.nested_lists(fl)
f = open(path_to_pa + 'updated/nested_lists.py', 'w')
f.write('nlists = ' + str(n_lists))
f.close()
def extract_statements(fl, version=0):
statements = {'instance': set([]), 'subclass': set([]), 'facts': set([]), 'agentNeeded': set([])}
try:
sys.path.append(path_to_pa+'updated')
import nested_lists
dictio = nested_lists.nlists[0]
except:
tup = parse_ontologies.nested_lists(fl, version)
dictio = tup[0]
f = open(path_to_pa+'updated/nested_lists.py', 'w')
f.write('nlists = '+str(tup))
f.close()
try:
if not abb.has_key(fl):
abbrev = abbr_n_vers[fl][0] # e.g. 'MD' for 'Media.kif'
except:
pass
actions = []
for tup in dictio:
formula = dictio[tup]
# a 'tup' looks like this --> (1047647, 1047670): ['subclass', 'Pollen', 'Object']
# Also, we will notice that everything is a subclass of itself (Naive set theory)
blacklisted = set(['documentation', '=>', 'domain',
'subAttribute', 'partition', 'range', 'relatedInternalConcept',
'disjointRelation', 'rangeSubclass', 'not', 'disjointDecomposition',
'synonymousExternalConcept', 'names', 'abbreviation', 'conventionalLongName',
'formerName', 'conventionalLongName', 'organizationalObjective',
'equal', 'subsumesContentClass', 'termFormat', 'externalImage',
'forall', 'longitude', 'format', 'exhaustiveDecomposition', 'dateEstablished',
'modalAttribute', 'lexicon', 'earthAltitude', 'latitude', 'located',
'depth', 'landAreaOnly', 'flowsInto',
'<=>', 'disjoint', 'subrelation', 'domainSubclass', 'contraryAttribute'])
if formula[0] == '=>' and formula[1][0] == 'and' and formula[2][0] == 'causesProposition' and formula[2][1][0] == 'and' and formula[2][2][0] == 'and':
actions.append(formula)
elif formula[0] == 'serviceProvider':
form2 = ['agentNeeded', formula[2], formula[1]]
statements['agentNeeded'].add(to_prolog(form2))
statements['facts'].add(to_prolog(formula))
elif not formula[0] in blacklisted:
a = to_prolog(formula)
if a: # i.e. if to_prolog has not returned None
if a[:5] == 'class':
statements['instance'].add(a)
elif a[:8] == 'subclass':
statements['subclass'].add(a)
else:
statements['facts'].add(a)
statements['actions'] = find_actions(actions)
return statements
def get_candidates(ontology):
"""
includes a recursive function which traverses the
trees (nested structures) in the ontology to decide
which terms ('concepts') are 'candidates' for
semantic matching. For instance, the following are
unlikely to change from one version to the other
so, they are not 'candidates':
-- built-in SUO-KIF operators such as 'and', 'not',
'or', '=>' and '<=>', as well as quantifiers such
as 'exists' and 'forall' because they are part of
the ontology language and not the ontology itself.
Pease, A. (2009) "Standard Upper Ontology Knowledge
Interchange Format", online.
-- fundamental SUMO concepts which we can assume as
known to ORS and very unlikely to change. Examples
are 'subclass', 'instance', 'documentation', 'domain',
'attribute', 'disjoint' etc.
"""
try:
sys.path.append(path_to_pa+'updated')
import nested_lists
tup = nested_lists.nlists
except:
tup = parse_ontologies.nested_lists(ontology)
f = open(path_to_pa+'updated/nested_lists.py', 'w')
f.write('nlists = '+str(tup))
f.close()
"""
The above tuple contains two dictionaries, one with nested
lists and one with comments. See the nested_lists function
in the data/parse_ontologies.py module.
"""
trees = tup[0]
comments = tup[1] # will use it later
excluded = set(['and', 'not', 'or', '=>', '<=>', 'forall', 'exists', 'subclass',
'instance', 'documentation', 'domain', 'attribute', 'disjoint',
'equal'])
candidates = []
def recursive_backtracking(item): # item can be a list or a string
if type(item) == str:
# exclude uninstantiated variables and phrases
if not item in excluded and not item[0] == '?' and not item[0] == '"' and not item in candidates and not is_number(item):
candidates.append(item)
else:
for thing in item:
recursive_backtracking(thing)
for tu in trees:
recursive_backtracking(trees[tu])
candidates.sort()
# To print 'candidates' in a file,
# comment out the following code:
"""
f = open(path_here+'candidates.txt', 'w')
f.write(str(candidates))
f.close()
"""
# candidates is a list of concepts in the input ontology
# which are 'candidates' for semantic matching
# e.g. ['SmokingPipe', 'Smuggling', 'Snake', 'Sober'...etc]
return candidates
