def __init__(self, store, edb, derivedPredicates=None, idb=None, DEBUG=False, nsBindings={}, templateMap=None, identifyHybridPredicates=False, hybridPredicates=None, existentialsInHeads=False, toldBNode=False, addRIFFacts=False, embedOWL=False): self.toldBNode = toldBNode self.existentialInHead = existentialsInHeads self.dataset = store hybridPredicates = hybridPredicates if hybridPredicates else [] if hasattr(store, '_db'): self._db = store._db self.idb = idb if idb else set() self.edb = edb for rifUri in edb.query(RIF_REFERENCE_QUERY): try: from FuXi.Horn.RIFCore import RIFCoreParser print rifUri if rifUri in map(lambda i: i.identifier, ConjunctiveGraph(edb.store).contexts()): if DEBUG: print "RIF in RDF is in named graph %s" % rifUri.n3() rif_parser = RIFCoreParser(graph=Graph(edb.store, rifUri), debug=DEBUG, owlEmbeddings=embedOWL) else: if DEBUG: print "RIF / XML is remote" rif_parser = RIFCoreParser(location=rifUri, debug=DEBUG, owlEmbeddings=embedOWL) rules, facts = rif_parser.getRuleset() if addRIFFacts and facts: #Add any ground facts in the referenced RIF graph #to the edb if DEBUG: print "Added %s statements from RIF document" % len( facts) print map(BuildUnitermFromTuple, facts) if isinstance(self.edb, ConjunctiveGraph): for fact in facts: self.edb.add(fact) else: self.edb.addN(map(lambda i: (i + (self.edb, )), facts)) self.idb.update(rules) except ImportError, e: raise Exception( "Missing 3rd party libraries for RIF processing: %s" % e) if DEBUG: pprint(list(self.idb))
def main(): from optparse import OptionParser op = OptionParser( 'usage: %prog [options] factFile1 factFile2 ... factFileN') op.add_option('--why', default=None, help='Specifies the goals to solve for') op.add_option( '--closure', action='store_true', default=False, help='Whether or not to serialize the inferred triples' + ' along with the original triples. Otherwise ' + '(the default behavior), serialize only the inferred triples') op.add_option( '--naive', action='store_true', default=False, help='Naively perform forward chaining over rules and facts using the ' + 'RETE network') op.add_option( '--imports', action='store_true', default=False, help='Whether or not to follow owl:imports in the fact graph') op.add_option( '--output', default='n3', metavar='RDF_FORMAT', choices=[ 'xml', 'TriX', 'n3', 'pml', 'proof-graph', 'nt', 'rif', 'rif-xml', 'conflict', 'man-owl' ], help= "Serialize the inferred triples and/or original RDF triples to STDOUT " + "using the specified RDF syntax ('xml','pretty-xml','nt','turtle', " + "or 'n3') or to print a summary of the conflict set (from the RETE " + "network) if the value of this option is 'conflict'. If the the " + " value is 'rif' or 'rif-xml', Then the rules used for inference " + "will be serialized as RIF. If the value is 'pml' and --why is used, " + " then the PML RDF statements are serialized. If output is " + "'proof-graph then a graphviz .dot file of the proof graph is printed. " + "Finally if the value is 'man-owl', then the RDF facts are assumed " + "to be OWL/RDF and serialized via Manchester OWL syntax. The default is %default" ) op.add_option( '--class', dest='classes', action='append', default=[], metavar='QNAME', help='Used with --output=man-owl to determine which ' + 'classes within the entire OWL/RDF are targetted for serialization' + '. Can be used more than once') op.add_option( '--hybrid', action='store_true', default=False, help='Used to determine whether or not to ' + 'peek into the fact graph to identify predicates that are both ' + 'derived and base. This is expensive for large fact graphs' + 'and is explicitely not used against SPARQL endpoints') op.add_option( '--property', action='append', dest='properties', default=[], metavar='QNAME', help='Used with --output=man-owl or --extract to determine which ' + 'properties are serialized / extracted. Can be used more than once') op.add_option( '--normalize', action='store_true', default=False, help= "Used with --output=man-owl to attempt to determine if the ontology is 'normalized' [Rector, A. 2003]" + "The default is %default") op.add_option( '--ddlGraph', default=False, help= "The location of a N3 Data Description document describing the IDB predicates" ) op.add_option( '--input-format', default='xml', dest='inputFormat', metavar='RDF_FORMAT', choices=['xml', 'trix', 'n3', 'nt', 'rdfa'], help= "The format of the RDF document(s) which serve as the initial facts " + " for the RETE network. One of 'xml','n3','trix', 'nt', " + "or 'rdfa'. The default is %default") op.add_option( '--safety', default='none', metavar='RULE_SAFETY', choices=['loose', 'strict', 'none'], help="Determines how to handle RIF Core safety. A value of 'loose' " + " means that unsafe rules will be ignored. A value of 'strict' " + " will cause a syntax exception upon any unsafe rule. A value of " + "'none' (the default) does nothing") op.add_option( '--pDSemantics', action='store_true', default=False, help= 'Used with --dlp to add pD semantics ruleset for semantics not covered ' + 'by DLP but can be expressed in definite Datalog Logic Programming' + ' The default is %default') op.add_option( '--stdin', action='store_true', default=False, help= 'Parse STDIN as an RDF graph to contribute to the initial facts. The default is %default ' ) op.add_option( '--ns', action='append', default=[], metavar="PREFIX=URI", help='Register a namespace binding (QName prefix to a base URI). This ' + 'can be used more than once') op.add_option( '--rules', default=[], action='append', metavar='PATH_OR_URI', help='The Notation 3 documents to use as rulesets for the RETE network' + '. Can be specified more than once') op.add_option('-d', '--debug', action='store_true', default=False, help='Include debugging output') op.add_option( '--strictness', default='defaultBase', metavar='DDL_STRICTNESS', choices=['loose', 'defaultBase', 'defaultDerived', 'harsh'], help= 'Used with --why to specify whether to: *not* check if predicates are ' + ' both derived and base (loose), if they are, mark as derived (defaultDerived) ' + 'or as base (defaultBase) predicates, else raise an exception (harsh)') op.add_option( '--firstAnswer', default=False, action='store_true', help= 'Used with --why to determine whether to fetch all answers or just ' + 'the first') op.add_option( '--edb', default=[], action='append', metavar='EXTENSIONAL_DB_PREDICATE_QNAME', help= 'Used with --why/--strictness=defaultDerived to specify which clashing ' + 'predicate will be designated as a base predicate') op.add_option( '--idb', default=[], action='append', metavar='INTENSIONAL_DB_PREDICATE_QNAME', help= 'Used with --why/--strictness=defaultBase to specify which clashing ' + 'predicate will be designated as a derived predicate') op.add_option( '--hybridPredicate', default=[], action='append', metavar='PREDICATE_QNAME', help= 'Used with --why to explicitely specify a hybrid predicate (in both ' + ' IDB and EDB) ') op.add_option( '--noMagic', default=[], action='append', metavar='DB_PREDICATE_QNAME', help='Used with --why to specify that the predicate shouldnt have its ' + 'magic sets calculated') op.add_option( '--filter', action='append', default=[], metavar='PATH_OR_URI', help= 'The Notation 3 documents to use as a filter (entailments do not particpate in network)' ) op.add_option( '--ruleFacts', action='store_true', default=False, help="Determines whether or not to attempt to parse initial facts from " + "the rule graph. The default is %default") op.add_option( '--builtins', default=False, metavar='PATH_TO_PYTHON_MODULE', help="The path to a python module with function definitions (and a " + "dicitonary called ADDITIONAL_FILTERS) to use for builtins implementations" ) op.add_option( '--dlp', action='store_true', default=False, help= 'Use Description Logic Programming (DLP) to extract rules from OWL/RDF. The default is %default' ) op.add_option( '--sparqlEndpoint', action='store_true', default=False, help= 'Indicates that the sole argument is the URI of a SPARQL endpoint to query' ) op.add_option( '--ontology', action='append', default=[], metavar='PATH_OR_URI', help= 'The path to an OWL RDF/XML graph to use DLP to extract rules from ' + '(other wise, fact graph(s) are used) ') op.add_option( '--ruleFormat', default='n3', dest='ruleFormat', metavar='RULE_FORMAT', choices=['n3', 'rif'], help= "The format of the rules to parse ('n3', 'rif'). The default is %default" ) op.add_option( '--ontologyFormat', default='xml', dest='ontologyFormat', metavar='RDF_FORMAT', choices=['xml', 'trix', 'n3', 'nt', 'rdfa'], help= "The format of the OWL RDF/XML graph specified via --ontology. The default is %default" ) op.add_option( '--builtinTemplates', default=None, metavar='N3_DOC_PATH_OR_URI', help= 'The path to an N3 document associating SPARQL FILTER templates to ' + 'rule builtins') op.add_option( '--normalForm', action='store_true', default=False, help='Whether or not to reduce DL axioms & LP rules to a normal form') (options, facts) = op.parse_args() nsBinds = {'iw': 'http://inferenceweb.stanford.edu/2004/07/iw.owl#'} for nsBind in options.ns: pref, nsUri = nsBind.split('=') nsBinds[pref] = nsUri namespace_manager = NamespaceManager(Graph()) if options.sparqlEndpoint: factGraph = Graph(plugin.get('SPARQL', Store)(facts[0])) options.hybrid = False else: factGraph = Graph() ruleSet = Ruleset() for fileN in options.rules: if options.ruleFacts and not options.sparqlEndpoint: factGraph.parse(fileN, format='n3') print >> sys.stderr, "Parsing RDF facts from ", fileN if options.builtins: import imp userFuncs = imp.load_source('builtins', options.builtins) rs = HornFromN3(fileN, additionalBuiltins=userFuncs.ADDITIONAL_FILTERS) nsBinds.update(rs.nsMapping) elif options.ruleFormat == 'rif': try: from FuXi.Horn.RIFCore import RIFCoreParser rif_parser = RIFCoreParser(location=fileN, debug=options.debug, nsBindings=nsBinds) rs, facts = rif_parser.getRuleset() except ImportError, e: raise Exception( "Missing 3rd party libraries for RIF processing: %s" % e) else: rs = HornFromN3(fileN) nsBinds.update(rs.nsMapping) ruleSet.formulae.extend(rs)