def convert_stop_times(self, csv_filename):
read_stop_times = self.__open_file(csv_filename)
for row in read_stop_times:
stop_id = str.strip(row["stop_id"])
sequence_num = str.strip(row["stop_sequence"])
trip_id = str.strip(row["trip_id"])
stop_time = Resource(self.graph, URIRef(self.uri + trip_id + "_" + stop_id + "_StopTime_" + sequence_num))
stop_time.set(RDF.type, self.GTFS.StopTime)
stop_time.add(self.GTFS.trip, self.get_trip(trip_id))
stop_time.add(self.GTFS.arrivalTime, Literal(str.strip(row["arrival_time"]), datatype=XSD.time))
stop_time.add(self.GTFS.departureTime, Literal(str.strip(row["departure_time"]), datatype=XSD.time))
stop_time.add(self.GTFS.stop, self.get_stop(stop_id))
stop_time.add(self.GTFS.stopSequence, Literal(sequence_num, datatype=XSD.nonNegativeInteger))
if "stop_headsign" in row:
stop_time.add(self.GTFS.headsign, Literal(str.strip(row["stop_headsign"]), datatype=XSD.string))
if "pickup_type" in row:
pickup_type = self.get_stop_type(str.strip(row["pickup_type"]))
stop_time.add(self.GTFS.pickupType, pickup_type)
if "drop_off_type" in row:
dropoff_type = self.get_stop_type(str.strip(row["drop_off_type"]))
stop_time.add(self.GTFS.dropOffType, dropoff_type)
if "shape_dist_traveled" in row:
# stop_time.add(self.GTFS.distanceTraveled,
# Literal(float(str.strip(row["shape_dist_traveled"])), datatype=XSD.nonNegativeInteger))
stop_time.add(self.GTFS.distanceTraveled, Literal(float(str.strip(row["shape_dist_traveled"]))))
def _vcard_name(self):
g = Graph()
vc = Resource(g, URIRef(self.vcard_name_uri))
vc.set(RDF.type, VCARD.Name)
vc.set(RDFS.label, Literal(self._label()))
vc.set(VCARD.familyName, Literal(self.cffamilynames))
vc.set(VCARD.givenName, Literal(self.cffirstnames))
if hasattr(self, 'middlename'):
vc.set(VIVO.middleName, Literal(self.middlename))
return g
def unified_orgs(self):
g = Graph()
addresses = self.addresses()
for addr in addresses:
for org in addr["unified_orgs"]:
uri = waan_uri(org)
r = Resource(g, uri)
r.set(RDF.type, WOS.UnifiedOrganization)
r.set(RDFS.label, Literal(org))
# relation set by address
return g
def to_rdf(self):
g = Graph()
o = Resource(g, self.uri)
o.set(RDF.type, FOAF.Organization)
o.set(RDFS.label, Literal(self.cfname))
o.set(CONVERIS.converisId, Literal(self.cid))
if hasattr(self, 'cfresact'):
o.set(VIVO.overview, Literal(self.cfresact))
for child in self.get_children():
# Has sub-organization
o.set(OBO['BFO_0000051'], child)
return g
def convert_calendar_dates(self, csv_filename):
read_dates = self.__open_file(csv_filename)
for row in read_dates:
service = self.get_service(str.strip(row["service_id"]))
calendar_date = Resource(self.graph, URIRef(self.uri + str.strip(row["service_id"]) + "_cal" + "_" + str.strip(row["date"])))
service.add(self.GTFS.serviceRule, calendar_date)
calendar_date.set(RDF.type, self.GTFS.CalendarDateRule)
calendar_date.add(DCTERMS.date, self.get_date_literal(str.strip(row["date"])))
exception_type = str.strip(row["exception_type"])
if exception_type is "2":
exception_type = "0"
calendar_date.add(self.GTFS.dateAddition, Literal(exception_type, datatype=XSD.boolean))
def convert_transfers(self, csv_filename):
read_transfers = self.__open_file(csv_filename)
for row in read_transfers:
from_stop = str.strip(row["from_stop_id"])
to_stop = str.strip(row["to_stop_id"])
transfers = Resource(self.graph, URIRef(self.uri + "_" + from_stop + "_" + to_stop))
transfers.set(RDF.type, self.GTFS.TransferRule)
transfers.add(self.GTFS.originStop, self.get_stop(from_stop))
transfers.add(self.GTFS.destinationStop, self.get_stop(to_stop))
transfers.add(self.GTFS.transferType, self.get_transfer_type(str.strip(row["transfer_type"])))
if "min_transfer_time" in row and str.strip(row["min_transfer_time"]):
transfers.add(self.GTFS.minimumTransferTime, Literal(str.strip(row["min_transfer_time"]), datatype=XSD.nonNegativeInteger))
def convert_shapes(self, csv_filename):
read_shapes = self.__open_file(csv_filename)
for row in read_shapes:
shape = self.get_shape(str.strip(row["shape_id"]))
shape_point = Resource(self.graph, URIRef(str(shape.identifier) + "_" + str.strip(row["shape_pt_sequence"])))
shape.add(self.GTFS.shapePoint, shape_point)
shape_point.set(RDF.type, self.GTFS.ShapePoint)
shape_point.set(self.GEO.long, Literal(str.strip(row["shape_pt_lon"]), datatype=XSD.string))
shape_point.set(self.GEO.lat, Literal(str.strip(row["shape_pt_lat"]), datatype=XSD.string))
shape_point.set(self.GTFS.pointSequence, Literal(str.strip(row["shape_pt_sequence"]), datatype=XSD.nonNegativeInteger))
if "shape_dist_traveled" in row and str.strip(row["shape_dist_traveled"]) != "":
shape_point.set(self.GTFS.distanceTraveled, Literal(str.strip(row["shape_dist_traveled"]),
datatype=XSD.nonNegativeInteger))
def to_rdf(self):
g = Graph()
e = Resource(g, self.uri)
e.set(RDF.type, VIVO.Position)
e.set(CONVERIS.converisId, Literal(self.cid))
# Check jobtitle and function for position name.
if hasattr(self, 'jobtitle'):
title = self.jobtitle
elif hasattr(self, 'function'):
title = self.function['value']
else:
title = "Research"
e.set(RDFS.label, Literal(title))
# start/end
try:
start = self.cfstartdate
except AttributeError:
start = None
pass
try:
end = self.cfenddate
except AttributeError:
end = None
pass
# Add datetime interval
try:
dti_uri, dti_g = self.get_dti(start, end)
g += dti_g
e.set(VIVO.dateTimeInterval, dti_uri)
except TypeError:
pass
return g
def convert_frequencies(self, csv_filename):
read_freqs = self.__open_file(csv_filename)
for row in read_freqs:
freq = Resource(self.graph, URIRef(self.uri + str.strip(row["trip_id"]) + str.strip(row["start_time"]) + str.strip(row["end_time"])))
freq.set(RDF.type, self.GTFS.Frequency)
freq.add(self.GTFS.trip, self.get_trip(str.strip(row["trip_id"])))
freq.add(self.GTFS.startTime, Literal(str.strip(row["start_time"]), datatype=XSD.string))
freq.add(self.GTFS.endTime, Literal(str.strip(row["end_time"]), datatype=XSD.string))
freq.add(self.GTFS.headwaySeconds, Literal(str.strip(row["headway_secs"]), datatype=XSD.nonNegativeInteger))
if "exact_times" in row:
exact = False
if str.strip(row["exact_times"]) == "1":
exact = True
freq.add(self.GTFS.exactTimes, Literal(exact, datatype=XSD.boolean))
def process(self, input, output):
username = "******"
password = "******"
lmClient = LifemapperClient(username, password)
# Get the JSON spec
jsonSpecification = input.value(LM.hasJSONExperimentSpecificationURL)
# Get published scenario layers
scenarioLayerIDs = []
for layer in input[LM.hasScenarioLayer]:
layerID = layer.value(LM.hasLayerID)
scenarioLayerIDs.append(str(layerID))
# Post scenario and save ID
lmClient.postScenario(scenarioLayerIDs)
#scenarioID = str(234)
scenarioID = lmClient.getScenarioID()
scenarioURL = lmClient.getScenarioURL()
# The URI generator
resourceURI = ResourceURI()
# Create the published scenario
scenario = RDFLibResource(output.graph, resourceURI.getURI("scenario"))
ScenarioClass = RDFLibResource(output.graph, LM.Scenario)
scenario.set(RDF.type, ScenarioClass)
scenario.set(LM.hasScenarioID, Literal(scenarioID))
scenario.set(LM.hasScenarioURL, Literal(scenarioURL))
scenario.set(LM.hasJSONExperimentSpecificationURL, jsonSpecification)
# Add scenarioID to output
output.set(LM.hasPublishedScenario, scenario)
def to_rdf(self):
data = self.profile
g = Graph()
person = Resource(g, self.uri)
person.set(RDF.type, FOAF.Person)
names = data['full_names'].split("|")
full_name = max(names, key=len)
person.set(RDFS.label, Literal(full_name.strip()))
# For sorting
#person.set(FOAF.familyName, Literal(data['lastName']))
#person.set(WOS.alphaBrowse, Literal(data['lastName'][0].lower()))
# dais
for did in self.dais_ids:
person.set(WOS.daisNg, Literal(did))
# Vcard individual
vci_uri = self.vcard_uri
person.set(OBO['ARG_2000028'], vci_uri)
g.add((vci_uri, RDF.type, VCARD.Individual))
# Vcard Name
#g += self._vcard_name()
#g.add((vci_uri, VCARD.hasName, URIRef(self.vcard_name_uri)))
# Vcard email
vte = self._vcard_email()
if vte is not None:
g += vte
g.add((vci_uri, VCARD.hasEmail, URIRef(self.vcard_email_uri)))
return g
def add_venue(self):
"""
Add publication venue.
:return: rdflib.Graph
"""
g = Graph()
isbn = self.isbn()
issn = self.issn() or self.eissn()
if isbn is not None:
vtype = BIBO.Book
uri = D['venue-' + isbn]
elif issn is not None:
vtype = BIBO.Journal
uri = D['venue-' + issn]
else:
# Place holder
logger.info("No source/venue ISSN or ISBN found for {}.".format(self.ut()))
vtype = BIBO.Journal
uri = D['venue-' + self.localid]
venue = Resource(g, uri)
venue.set(RDF.type, vtype)
venue.set(RDFS.label, Literal(self.venue()))
if vtype == BIBO.Journal:
venue.set(BIBO.issn, Literal(issn))
else:
venue.set(BIBO.isbn, Literal(isbn))
g.add((self.pub_uri, VIVO.hasPublicationVenue, uri))
return g
def convert_feed(self, csv_filename):
read_feed = self.__open_file(csv_filename)
for row in read_feed:
feed = Resource(self.graph, URIRef(str.strip(row["publisher"])))
feed.set(RDF.type, self.GTFS.Feed)
feed.add(DCTERMS.publisher, Literal(str.strip(row["publisher"]), datatype=XSD.string))
feed.add(DCTERMS.title, Literal(str.strip(row["feed_publisher_name"]), datatype=XSD.string))
feed.add(DCTERMS.language, Literal(str.strip(row["feed_lang"]), datatype=XSD.string))
if "feed_version" in row and str.strip(row["feed_version"]) != "":
feed.add(self.SCHEMA.version, Literal(row["feed_version"], datatype=XSD.string))
if "feed_start_date" in row and str.strip(row["feed_start_date"]) != "" and "feed_end_date" in row and str.strip(row["feed_end_date"]) != "":
temporal = Resource(self.graph, URIRef(feed.identifier + "_temporal"))
temporal.set(RDF.type, DCTERMS.temporal)
temporal.add(self.SCHEMA.startDate, self.get_date_literal(str.strip(row["feed_start_date"])))
temporal.add(self.SCHEMA.endDate, self.get_date_literal(str.strip(row["feed_end_date"])))
def convert_fare_rules(self, csv_filename):
read_fares = self.__open_file(csv_filename)
for row in read_fares:
fare = self.get_fare(str.strip(row["fare_id"]))
fare_rule = Resource(self.graph, URIRef(self.uri + str.strip(row["fare_id"]) + "_rule_" + str(self.next_fare_rule_num)))
self.next_fare_rule_num += 1
fare_rule.set(RDF.type, self.GTFS.FareRule)
fare_rule.set(self.GTFS.fareClass, fare_rule)
if "route_id" in row and str.strip(row["route_id"]) != "":
fare_rule.add(self.GTFS.route, self.get_route(str.strip(row["route_id"])))
if "origin_id" in row and str.strip(row["origin_id"]) != "":
fare_rule.add(self.GTFS.originZone, self.get_zone(str.strip(row["origin_id"])))
if "destination_id" in row and str.strip(row["destination_id"]) != "":
fare_rule.add(self.GTFS.destinationZone, self.get_zone(str.strip(row["destination_id"])))
if "contains_id" in row and str.strip(row["contains_id"]) != "":
fare_rule.add(self.GTFS.zone, self.get_zone(str.strip(row["contains_id"])))
def _date(self, dtype, dv):
g = Graph()
date_obj = converis.convert_date(dv)
date_uri = URIRef(DATA_NAMESPACE + 'date' + dtype + self.vid)
de = Resource(g, date_uri)
de.set(RDF.type, VIVO.DateTimeValue)
if date_obj is not None:
de.set(RDFS.label, Literal(dv))
de.set(VIVO.dateTime, Literal(date_obj, datatype=XSD.date))
de.set(VIVO.dateTimePrecision, VIVO.yearMonthDayPrecision)
return date_uri, g
def to_rdf(self):
g = Graph()
p = Resource(g, self.uri)
p.add(RDF.type, FOAF.Person)
p.set(RDFS.label, Literal(self._label()))
p.set(CONVERIS.converisId, Literal(self.cid))
if hasattr(self, 'cfresint'):
p.set(VIVO.researchOverview, Literal(self.cfresint))
if hasattr(self, 'orcid'):
p.set(VIVO.orcidId, self.orcid_uri)
# Confirm the orcid
g.add((self.orcid_uri, RDF.type, OWL.Thing))
# Todo - review if we want to confirm all orcids
g.add((self.orcid_uri, VIVO.confirmedOrcidId, self.uri))
# Vcard individual
vci_uri = URIRef(self.vcard_uri)
p.set(OBO['ARG_2000028'], vci_uri)
g.add((vci_uri, RDF.type, VCARD.Individual))
# Vcard Name
g += self._vcard_name()
g.add((vci_uri, VCARD.hasName, URIRef(self.vcard_name_uri)))
# Vcard title
vtg = self._vcard_title()
if vtg is not None:
g += vtg
g.add((vci_uri, VCARD.hasTitle, URIRef(self.vcard_title_uri)))
# Vcard email
vte = self._vcard_email()
if vte is not None:
g += vte
g.add((vci_uri, VCARD.hasEmail, URIRef(self.vcard_email_uri)))
# positions
g += self.get_positions()
return g
def to_rdf(self):
g = Graph()
r = Resource(g, self.uri)
r.set(RDF.type, SKOS.Concept)
r.set(RDFS.label, Literal(self.name))
r.set(CONVERIS.converisId, Literal(self.cid))
return g
def _vcard_title(self):
title = self.profile['position_title']
g = Graph()
vt = Resource(g, self.vcard_title_uri)
vt.set(RDF.type, VCARD.Title)
vt.set(RDFS.label, Literal(title))
vt.set(VCARD.title, Literal(title))
return g
def sub_orgs(self):
g = Graph()
addresses = self.addresses()
for addr in addresses:
ano = addr["number"]
org = addr["organization"]
for idx, suborg in enumerate(addr['sub_organizations']):
label = "{}, {}".format(suborg, org)
uri = self.sub_org_uri(label)
r = Resource(g, uri)
r.set(RDF.type, WOS.SubOrganization)
r.set(RDFS.label, Literal(label))
r.set(WOS.organizationName, Literal(org))
r.set(WOS.subOrganizationName, Literal(suborg))
return g
def _vcard_name(self):
g = Graph()
vc = Resource(g, URIRef(self.vcard_name_uri))
vc.set(RDF.type, VCARD.Name)
vc.set(RDFS.label, Literal(self.profile['name'].strip()))
vc.set(VCARD.familyName, Literal(self.profile['lastName']))
vc.set(VCARD.givenName, Literal(self.profile['firstName']))
return g
def _vcard_title(self):
if not hasattr(self, 'academictitle'):
return None
g = Graph()
vt = Resource(g, self.vcard_title_uri)
vt.set(RDF.type, VCARD.Title)
vt.set(RDFS.label, Literal(self.academictitle))
vt.set(VCARD.title, Literal(self.academictitle))
return g
def to(self):
"""
Core publication metadata mapped to VIVO RDF.
:return: Graph
"""
g = Graph()
r = Resource(g, self.uri)
r.set(RDFS.label, Literal(self.title()))
for vtype in self.rec_type():
r.add(RDF.type, vtype)
r.set(WOS.wosId, Literal(self.ut))
meta = self.meta()
# data properties
data_props = [
#('author_list', WOS.authorList),
('abstract', BIBO.abstract),
('funding_acknowledgement', WOS.fundingText),
('volume', BIBO.volume),
('issue', BIBO.issue),
('start', BIBO.pageStart),
('end', BIBO.pageEnd),
('page_count', BIBO.numPages),
('doi', BIBO.doi),
#('cite_key', WOS.citeKey),
('reference_count', WOS.referenceCount),
('citation_count', WOS.citationCount)
]
for key, prop in data_props:
value = meta.get(key)
if value is not None:
g.add((self.uri, prop, Literal(value)))
g += self.add_pub_date()
return g
def addressships(self):
g = Graph()
addresses = self.addresses()
for addr in addresses:
addr_uri = self.addr_uri(addr["full_address"], addr["number"])
org = addr["organization"]
r = Resource(g, addr_uri)
r.set(RDF.type, WOS.Address)
r.set(RDFS.label, Literal(addr['full_address']))
r.set(WOS.organizationName, Literal(org))
r.set(WOS.sequenceNumber, Literal(addr['number']))
# relation to author set by authorship
# relate to pub
r.set(VIVO.relates, self.uri)
# sub orgs
for idx, suborg in enumerate(addr["sub_organizations"]):
label = "{}, {}".format(suborg, org)
so_uri = self.sub_org_uri(label)
r.add(VIVO.relates, so_uri)
# relate unified orgs
for uorg in addr["unified_orgs"]:
uo_uri = waan_uri(uorg)
r.add(VIVO.relates, uo_uri)
return g
def to_rdf(self):
g = Graph()
r = Resource(g, self.uri)
r.set(RDF.type, SKOS.Concept)
r.set(RDFS.label, Literal(self.name))
r.set(CONVERIS.converisId, Literal(self.cid))
g += self.has_researchers()
g += self.get_narrower()
return g
def _vcard_email(self):
if not hasattr(self, 'email'):
return None
g = Graph()
vt = Resource(g, self.vcard_email_uri)
vt.set(RDF.type, VCARD.Email)
# Label probably not necessary
vt.set(RDFS.label, Literal(self.email))
vt.set(VCARD.email, Literal(self.email))
return g
def add_pub_date(self):
"""
Publication dates in VIVO's expected format.
"""
g = Graph()
value = self.pub_date()
if value is None:
return g
date_uri = self.make_date_uri(self.ut, value)
date = Resource(g, date_uri)
date.set(RDF.type, VIVO.DateTimeValue)
date.set(VIVO.dateTimePrecision, VIVO.yearMonthDayPrecision)
date.add(VIVO.dateTime,
Literal("%sT00:00:00" % (value), datatype=XSD.dateTime))
date.add(RDFS.label, Literal(value))
date.set(RDF.type, VIVO.DateTimeValue)
date.set(VIVO.dateTimePrecision, VIVO.yearMonthDayPrecision)
date.add(VIVO.dateTime,
Literal("%sT00:00:00" % (value), datatype=XSD.dateTime))
date.add(RDFS.label, Literal(value))
g.add((self.uri, VIVO.dateTimeValue, date_uri))
return g
def process(self, input, output):
username = "******"
password = "******"
lmClient = LifemapperClient(username, password)
# Get scenario id
scenario = input.value(LM.specifiesModellingScenario)
scenarioID = scenario.value(LM.hasScenarioID)
# Extract Algorithm
algorithm = input.value(LM.specifiesModellingAlgorithm)
algorithmCode = algorithm.value(LM.hasAlgorithmCode)
# Extract Parameter Bindings
params = algorithm.value(MD.behaviorControlledBy)
bindings = []
for param in params[MD.hasParameterMember]:
name = param.value(MD.hasParameterName)
value = param.value(MD.boundToValue)
bindings[name] = value
# Extract OccurrenceSetID
occurrenceSet = input.value(LM.specifiesOccurrenceSet)
occurrenceSetID = occurrenceSet.value(LM.hasOccurrenceSetID)
lmClient.postExperiment(algorithmCode, bindings, occurrenceSetID, scenarioID)
#resultURL = "http://somedomain.com/testURL"
#get experimentURL and id
experimentURL = lmClient.getExperimentURL()
experimentID = lmClient.getExperimentID()
print "experiment result URL %s " % experimentURL
# The URI generator
resourceURI = ResourceURI()
# Create the experiment result
experimentResult = RDFLibResource(output.graph, resourceURI.getURI("experimentResult"))
experimentResultClass = RDFLibResource(output.graph, LM.ExperimentResult)
experimentResult.set(RDF.type, experimentResultClass)
experimentResult.set(LM.hasExperimentResultURL, Literal(experimentURL))
experimentResult.set(LM.hasExperimentResultID, Literal(experimentID))
# Add the experiment result to the executed specification
output.set(LM.hasExperimentResult, experimentResult)
def _vcard_email(self):
g = Graph()
try:
emails = [e for e in self.profile["emails"].split("|")]
except KeyError:
try:
emails = [self.profile['email']]
except KeyError:
emails = []
for email in emails:
vt = Resource(g, self.vcard_email_uri)
vt.set(RDF.type, VCARD.Work)
# Label probably not necessary
vt.set(RDFS.label, Literal(email))
vt.set(VCARD.email, Literal(email))
return g
def authorships(self):
g = Graph()
aus = self.authors()
for au in aus:
aship_uri = self.aship_uri(au['rank'])
r = Resource(g, aship_uri)
r.set(RDFS.label, Literal(au["display_name"]))
r.set(RDF.type, VIVO.Authorship)
r.set(VIVO.rank, Literal(au['rank']))
data_props = [
('rank', VIVO.rank),
('full_name', WOS.fullName),
('display_name', WOS.displayName),
('wos_standard', WOS.standardName),
('first', WOS.firstName),
('last', WOS.lastName),
('email', WOS.email),
('dais_ng', WOS.daisNg),
('reprint', WOS.reprint),
]
for key, prop in data_props:
value = au.get(key)
if value is not None:
r.set(prop, Literal(value))
# relations
r.add(VIVO.relates, self.uri)
# relate to addresses too
# address nums are a space separated list of numbers
addr_nums = au["address"]
if addr_nums is None:
continue
else:
for anum in addr_nums.split():
addr_uris = self.addr_uris_from_number(anum)
for auri in addr_uris:
r.add(VIVO.relates, auri)
return g
def get_dti(self, start, end):
if (start is None) and (end is None):
return
# Date/Time Interval
g = Graph()
dti_uri = D['dti'] + self.vid
dti = Resource(g, dti_uri)
dti.set(RDF.type, VIVO.DateTimeInterval)
if start is not None:
start_uri, start_g = self._date("start", start)
dti.set(VIVO.start, start_uri)
g += start_g
if end is not None:
end_uri, end_g = self._date("end", end)
g += end_g
dti.set(VIVO.end, end_uri)
return dti_uri, g
def get_stop(self, stop_id):
stop = Resource(self.graph, URIRef(self.uri + "stop_" + stop_id))
stop.set(DCTERMS.identifier, Literal(stop_id, datatype=XSD.string))
return stop
def get_zone(self, zone_id):
the_zone = Resource(self.graph, URIRef(self.uri + "zone_" + zone_id))
the_zone.set(RDF.type, self.GTFS.Zone)
the_zone.set(DCTERMS.identifier, Literal(zone_id, datatype=XSD.string))
return the_zone
def get_route(self, route_id):
route = Resource(self.graph, URIRef(self.uri + "route_" + route_id))
route.set(RDF.type, self.GTFS.Route)
route.set(DCTERMS.identifier, Literal(route_id, datatype=XSD.string))
return route
def get_trip(self, trip_id):
trip = Resource(self.graph, URIRef(self.uri + "trip_" + trip_id))
trip.set(RDF.type, self.GTFS.Trip)
trip.set(DCTERMS.identifier, Literal(trip_id, datatype=XSD.string))
return trip
def get_service(self, service_id):
service = Resource(self.graph, URIRef(self.uri + "service_" + service_id))
service.set(RDF.type, self.GTFS.Service)
service.set(DCTERMS.identifier, Literal(service_id, datatype=XSD.string))
return service
class Ldpr(metaclass=ABCMeta):
'''LDPR (LDP Resource).
Definition: https://www.w3.org/TR/ldp/#ldpr-resource
This class and related subclasses contain the implementation pieces of
the vanilla LDP specifications. This is extended by the
`lakesuperior.fcrepo.Resource` class.
Inheritance graph: https://www.w3.org/TR/ldp/#fig-ldpc-types
Note: Even though LdpNr (which is a subclass of Ldpr) handles binary files,
it still has an RDF representation in the triplestore. Hence, some of the
RDF-related methods are defined in this class rather than in the LdpRs
class.
Convention notes:
All the methods in this class handle internal UUIDs (URN). Public-facing
URIs are converted from URNs and passed by these methods to the methods
handling HTTP negotiation.
The data passed to the store layout for processing should be in a graph.
All conversion from request payload strings is done here.
'''
EMBED_CHILD_RES_URI = nsc['fcrepo'].EmbedResources
FCREPO_PTREE_TYPE = nsc['fcrepo'].Pairtree
INS_CNT_REL_URI = nsc['ldp'].insertedContentRelation
MBR_RSRC_URI = nsc['ldp'].membershipResource
MBR_REL_URI = nsc['ldp'].hasMemberRelation
RETURN_CHILD_RES_URI = nsc['fcrepo'].Children
RETURN_INBOUND_REF_URI = nsc['fcrepo'].InboundReferences
RETURN_SRV_MGD_RES_URI = nsc['fcrepo'].ServerManaged
# Workflow type. Inbound means that the resource is being written to the
# store, outbounnd is being retrieved for output.
WRKF_INBOUND = '_workflow:inbound_'
WRKF_OUTBOUND = '_workflow:outbound_'
# Default user to be used for the `createdBy` and `lastUpdatedBy` if a user
# is not provided.
DEFAULT_USER = Literal('BypassAdmin')
# RDF Types that populate a new resource.
base_types = {
nsc['fcrepo'].Resource,
nsc['ldp'].Resource,
nsc['ldp'].RDFSource,
}
# Predicates that do not get removed when a resource is replaced.
protected_pred = (
nsc['fcrepo'].created,
nsc['fcrepo'].createdBy,
nsc['ldp'].contains,
)
# Server-managed RDF types ignored in the RDF payload if the resource is
# being created. N.B. These still raise an error if the resource exists.
smt_allow_on_create = {
nsc['ldp'].DirectContainer,
nsc['ldp'].IndirectContainer,
}
## MAGIC METHODS ##
def __init__(self, uid, repr_opts={}, provided_imr=None, **kwargs):
'''Instantiate an in-memory LDP resource that can be loaded from and
persisted to storage.
@param uid (string) uid of the resource. If None (must be explicitly
set) it refers to the root node. It can also be the full URI or URN,
in which case it will be converted.
@param repr_opts (dict) Options used to retrieve the IMR. See
`parse_rfc7240` for format details.
@Param provd_rdf (string) RDF data provided by the client in
operations such as `PUT` or `POST`, serialized as a string. This sets
the `provided_imr` property.
'''
self.uid = (rdfly.uri_to_uid(uid) if isinstance(uid, URIRef) else uid)
self.uri = nsc['fcres'][uid]
# @FIXME Not ideal, should separate app-context dependent functions in
# a different toolbox.
self.tbox = Toolbox()
self.provided_imr = provided_imr
@property
def rsrc(self):
'''
The RDFLib resource representing this LDPR. This is a live
representation of the stored data if present.
@return rdflib.resource.Resource
'''
if not hasattr(self, '_rsrc'):
self._rsrc = rdfly.ds.resource(self.uri)
return self._rsrc
@property
def imr(self):
'''
Extract an in-memory resource from the graph store.
If the resource is not stored (yet), a `ResourceNotExistsError` is
raised.
@return rdflib.resource.Resource
'''
if not hasattr(self, '_imr'):
if hasattr(self, '_imr_options'):
logger.debug(
'Getting RDF representation for resource {}'.format(
self.uid))
#logger.debug('IMR options:{}'.format(self._imr_options))
imr_options = self._imr_options
else:
imr_options = {}
options = dict(imr_options, strict=True)
self._imr = rdfly.extract_imr(self.uid, **options)
return self._imr
@imr.setter
def imr(self, v):
'''
Replace in-memory buffered resource.
@param v (set | rdflib.Graph) New set of triples to populate the IMR
with.
'''
if isinstance(v, Resource):
v = v.graph
self._imr = Resource(Graph(), self.uri)
gr = self._imr.graph
gr += v
@imr.deleter
def imr(self):
'''
Delete in-memory buffered resource.
'''
delattr(self, '_imr')
@property
def metadata(self):
'''
Get resource metadata.
'''
if not hasattr(self, '_metadata'):
if hasattr(self, '_imr'):
logger.info('Metadata is IMR.')
self._metadata = self._imr
else:
logger.info('Getting metadata for resource {}'.format(
self.uid))
self._metadata = rdfly.get_metadata(self.uid)
return self._metadata
@metadata.setter
def metadata(self, rsrc):
'''
Set resource metadata.
'''
if not isinstance(rsrc, Resource):
raise TypeError('Provided metadata is not a Resource object.')
self._metadata = rsrc
@property
def stored_or_new_imr(self):
'''
Extract an in-memory resource for harmless manipulation and output.
If the resource is not stored (yet), initialize a new IMR with basic
triples.
@return rdflib.resource.Resource
'''
if not hasattr(self, '_imr'):
if hasattr(self, '_imr_options'):
#logger.debug('IMR options:{}'.format(self._imr_options))
imr_options = self._imr_options
else:
imr_options = {}
options = dict(imr_options, strict=True)
try:
self._imr = rdfly.extract_imr(self.uid, **options)
except ResourceNotExistsError:
self._imr = Resource(Graph(), self.uri)
for t in self.base_types:
self.imr.add(RDF.type, t)
return self._imr
@property
def out_graph(self):
'''
Retun a graph of the resource's IMR formatted for output.
'''
out_gr = Graph(identifier=self.uri)
for t in self.imr.graph:
if (
# Exclude digest hash and version information.
t[1] not in {
nsc['premis'].hasMessageDigest,
nsc['fcrepo'].hasVersion,
}) and (
# Only include server managed triples if requested.
self._imr_options.get('incl_srv_mgd', True)
or not self._is_trp_managed(t)):
out_gr.add(t)
return out_gr
@property
def version_info(self):
'''
Return version metadata (`fcr:versions`).
'''
if not hasattr(self, '_version_info'):
try:
#@ TODO get_version_info should return a graph.
self._version_info = rdfly.get_version_info(self.uid).graph
except ResourceNotExistsError as e:
self._version_info = Graph(identifier=self.uri)
return self._version_info
@property
def version_uids(self):
'''
Return a generator of version UIDs (relative to their parent resource).
'''
gen = self.version_info[self.uri:nsc['fcrepo'].hasVersion /
nsc['fcrepo'].hasVersionLabel:]
return {str(uid) for uid in gen}
@property
def is_stored(self):
if not hasattr(self, '_is_stored'):
if hasattr(self, '_imr'):
self._is_stored = len(self.imr.graph) > 0
else:
self._is_stored = rdfly.ask_rsrc_exists(self.uid)
return self._is_stored
@property
def types(self):
'''All RDF types.
@return set(rdflib.term.URIRef)
'''
if not hasattr(self, '_types'):
if len(self.metadata.graph):
metadata = self.metadata
elif getattr(self, 'provided_imr', None) and \
len(self.provided_imr.graph):
metadata = self.provided_imr
else:
return set()
self._types = set(metadata.graph[self.uri:RDF.type])
return self._types
@property
def ldp_types(self):
'''The LDP types.
@return set(rdflib.term.URIRef)
'''
if not hasattr(self, '_ldp_types'):
self._ldp_types = {t for t in self.types if nsc['ldp'] in t}
return self._ldp_types
## LDP METHODS ##
def head(self):
'''
Return values for the headers.
'''
out_headers = defaultdict(list)
digest = self.metadata.value(nsc['premis'].hasMessageDigest)
if digest:
etag = digest.identifier.split(':')[-1]
out_headers['ETag'] = 'W/"{}"'.format(etag),
last_updated_term = self.metadata.value(nsc['fcrepo'].lastModified)
if last_updated_term:
out_headers['Last-Modified'] = arrow.get(last_updated_term)\
.format('ddd, D MMM YYYY HH:mm:ss Z')
for t in self.ldp_types:
out_headers['Link'].append('{};rel="type"'.format(t.n3()))
return out_headers
def get_version(self, ver_uid, **kwargs):
'''
Get a version by label.
'''
return rdfly.extract_imr(self.uid, ver_uid, **kwargs).graph
def create_or_replace(self, create_only=False):
'''
Create or update a resource. PUT and POST methods, which are almost
identical, are wrappers for this method.
@param create_only (boolean) Whether this is a create-only operation.
'''
pdb.set_trace()
create = create_only or not self.is_stored
ev_type = RES_CREATED if create else RES_UPDATED
self._add_srv_mgd_triples(create)
ref_int = rdfly.config['referential_integrity']
if ref_int:
self._check_ref_int(ref_int)
# Delete existing triples if replacing.
if not create:
rdfly.truncate_rsrc(self.uid)
remove_trp = {
(self.uri, nsc['fcrepo'].lastModified, None),
(self.uri, nsc['fcrepo'].lastModifiedBy, None),
}
add_trp = set(self.provided_imr.graph) | self._containment_rel(create)
self._modify_rsrc(ev_type, remove_trp, add_trp)
new_gr = Graph()
for trp in add_trp:
new_gr.add(trp)
self.imr = new_gr.resource(self.uri)
return ev_type
def put(self):
'''
https://www.w3.org/TR/ldp/#ldpr-HTTP_PUT
'''
return self.create_or_replace()
def patch(self, update_str):
'''
Update an existing resource by applying a SPARQL-UPDATE query.
@param update_str (string) SPARQL-Update staements.
'''
self.handling = 'lenient' # FCREPO does that and Hyrax requires it.
return self._sparql_update(update_str)
def bury_rsrc(self, inbound, tstone_pointer=None):
'''
Delete a single resource and create a tombstone.
@param inbound (boolean) Whether to delete the inbound relationships.
@param tstone_pointer (URIRef) If set to a URN, this creates a pointer
to the tombstone of the resource that used to contain the deleted
resource. Otherwise the deleted resource becomes a tombstone.
'''
logger.info('Burying resource {}'.format(self.uid))
# Create a backup snapshot for resurrection purposes.
self.create_rsrc_snapshot(uuid4())
remove_trp = {
trp
for trp in self.imr.graph if trp[1] != nsc['fcrepo'].hasVersion
}
if tstone_pointer:
add_trp = {(self.uri, nsc['fcsystem'].tombstone, tstone_pointer)}
else:
add_trp = {
(self.uri, RDF.type, nsc['fcsystem'].Tombstone),
(self.uri, nsc['fcrepo'].created, env.timestamp_term),
}
self._modify_rsrc(RES_DELETED, remove_trp, add_trp)
if inbound:
for ib_rsrc_uri in self.imr.graph.subjects(None, self.uri):
remove_trp = {(ib_rsrc_uri, None, self.uri)}
ib_rsrc = Ldpr(ib_rsrc_uri)
# To preserve inbound links in history, create a snapshot
ib_rsrc.create_rsrc_snapshot(uuid4())
ib_rsrc._modify_rsrc(RES_UPDATED, remove_trp)
return RES_DELETED
def forget_rsrc(self, inbound=True):
'''
Remove all traces of a resource and versions.
'''
logger.info('Purging resource {}'.format(self.uid))
refint = env.config['store']['ldp_rs']['referential_integrity']
inbound = True if refint else inbound
rdfly.forget_rsrc(self.uid, inbound)
# @TODO This could be a different event type.
return RES_DELETED
def create_rsrc_snapshot(self, ver_uid):
'''
Perform version creation and return the version UID.
'''
# Create version resource from copying the current state.
logger.info('Creating version snapshot {} for resource {}.'.format(
ver_uid, self.uid))
ver_add_gr = set()
vers_uid = '{}/{}'.format(self.uid, VERS_CONT_LABEL)
ver_uid = '{}/{}'.format(vers_uid, ver_uid)
ver_uri = nsc['fcres'][ver_uid]
ver_add_gr.add((ver_uri, RDF.type, nsc['fcrepo'].Version))
for t in self.imr.graph:
if (t[1] == RDF.type and t[2] in {
nsc['fcrepo'].Binary,
nsc['fcrepo'].Container,
nsc['fcrepo'].Resource,
}) or (t[1] in {
nsc['fcrepo'].hasParent,
nsc['fcrepo'].hasVersions,
nsc['fcrepo'].hasVersion,
nsc['premis'].hasMessageDigest,
}):
pass
else:
ver_add_gr.add(
(self.tbox.replace_term_domain(t[0], self.uri,
ver_uri), t[1], t[2]))
rdfly.modify_rsrc(ver_uid, add_trp=ver_add_gr)
# Update resource admin data.
rsrc_add_gr = {
(self.uri, nsc['fcrepo'].hasVersion, ver_uri),
(self.uri, nsc['fcrepo'].hasVersions, nsc['fcres'][vers_uid]),
}
self._modify_rsrc(RES_UPDATED, add_trp=rsrc_add_gr, notify=False)
return ver_uid
def resurrect_rsrc(self):
'''
Resurrect a resource from a tombstone.
@EXPERIMENTAL
'''
tstone_trp = set(rdfly.extract_imr(self.uid, strict=False).graph)
ver_rsp = self.version_info.graph.query('''
SELECT ?uid {
?latest fcrepo:hasVersionLabel ?uid ;
fcrepo:created ?ts .
}
ORDER BY DESC(?ts)
LIMIT 1
''')
ver_uid = str(ver_rsp.bindings[0]['uid'])
ver_trp = set(rdfly.get_metadata(self.uid, ver_uid).graph)
laz_gr = Graph()
for t in ver_trp:
if t[1] != RDF.type or t[2] not in {
nsc['fcrepo'].Version,
}:
laz_gr.add((self.uri, t[1], t[2]))
laz_gr.add((self.uri, RDF.type, nsc['fcrepo'].Resource))
if nsc['ldp'].NonRdfSource in laz_gr[:RDF.type:]:
laz_gr.add((self.uri, RDF.type, nsc['fcrepo'].Binary))
elif nsc['ldp'].Container in laz_gr[:RDF.type:]:
laz_gr.add((self.uri, RDF.type, nsc['fcrepo'].Container))
laz_set = set(laz_gr) | self._containment_rel()
self._modify_rsrc(RES_CREATED, tstone_trp, laz_set)
return self.uri
def create_version(self, ver_uid=None):
'''
Create a new version of the resource.
NOTE: This creates an event only for the resource being updated (due
to the added `hasVersion` triple and possibly to the `hasVersions` one)
but not for the version being created.
@param ver_uid Version ver_uid. If already existing, an exception is
raised.
'''
if not ver_uid or ver_uid in self.version_uids:
ver_uid = str(uuid4())
return self.create_rsrc_snapshot(ver_uid)
def revert_to_version(self, ver_uid, backup=True):
'''
Revert to a previous version.
@param ver_uid (string) Version UID.
@param backup (boolean) Whether to create a backup snapshot. Default is
true.
'''
# Create a backup snapshot.
if backup:
self.create_version()
ver_gr = rdfly.extract_imr(self.uid,
ver_uid=ver_uid,
incl_children=False)
self.provided_imr = Resource(Graph(), self.uri)
for t in ver_gr.graph:
if not self._is_trp_managed(t):
self.provided_imr.add(t[1], t[2])
# @TODO Check individual objects: if they are repo-managed URIs
# and not existing or tombstones, they are not added.
return self.create_or_replace(create_only=False)
## PROTECTED METHODS ##
def _is_trp_managed(self, t):
'''
Whether a triple is server-managed.
@return boolean
'''
return t[1] in srv_mgd_predicates or (t[1] == RDF.type
and t[2] in srv_mgd_types)
def _modify_rsrc(self,
ev_type,
remove_trp=set(),
add_trp=set(),
notify=True):
'''
Low-level method to modify a graph for a single resource.
This is a crucial point for messaging. Any write operation on the RDF
store that needs to be notified should be performed by invoking this
method.
@param ev_type (string) The type of event (create, update, delete).
@param remove_trp (set) Triples to be removed.
@param add_trp (set) Triples to be added.
@param notify (boolean) Whether to send a message about the change.
'''
rdfly.modify_rsrc(self.uid, remove_trp, add_trp)
if notify and env.config['application'].get('messaging'):
logger.debug('Enqueuing message for {}'.format(self.uid))
self._enqueue_msg(ev_type, remove_trp, add_trp)
def _enqueue_msg(self, ev_type, remove_trp=None, add_trp=None):
'''
Compose a message about a resource change.
The message is enqueued for asynchronous processing.
@param ev_type (string) The event type. See global constants.
@param remove_trp (set) Triples removed. Only used if the
'''
try:
rsrc_type = tuple(str(t) for t in self.types)
actor = self.metadata.value(nsc['fcrepo'].createdBy)
except (ResourceNotExistsError, TombstoneError):
rsrc_type = ()
actor = None
for t in add_trp:
if t[1] == RDF.type:
rsrc_type.add(t[2])
elif actor is None and t[1] == nsc['fcrepo'].createdBy:
actor = t[2]
env.app_globals.changelog.append((set(remove_trp), set(add_trp), {
'ev_type': ev_type,
'timestamp': env.timestamp.format(),
'rsrc_type': rsrc_type,
'actor': actor,
}))
def _check_ref_int(self, config):
gr = self.provided_imr.graph
for o in gr.objects():
if isinstance(o, URIRef) and str(o).startswith(nsc['fcres']):
obj_uid = rdfly.uri_to_uid(o)
if not rdfly.ask_rsrc_exists(obj_uid):
if config == 'strict':
raise RefIntViolationError(obj_uid)
else:
logger.info(
'Removing link to non-existent repo resource: {}'.
format(obj_uid))
gr.remove((None, None, o))
def _check_mgd_terms(self, gr):
'''
Check whether server-managed terms are in a RDF payload.
@param gr (rdflib.Graph) The graph to validate.
'''
offending_subjects = set(gr.subjects()) & srv_mgd_subjects
if offending_subjects:
if self.handling == 'strict':
raise ServerManagedTermError(offending_subjects, 's')
else:
for s in offending_subjects:
logger.info('Removing offending subj: {}'.format(s))
gr.remove((s, None, None))
offending_predicates = set(gr.predicates()) & srv_mgd_predicates
# Allow some predicates if the resource is being created.
if offending_predicates:
if self.handling == 'strict':
raise ServerManagedTermError(offending_predicates, 'p')
else:
for p in offending_predicates:
logger.info('Removing offending pred: {}'.format(p))
gr.remove((None, p, None))
offending_types = set(gr.objects(predicate=RDF.type)) & srv_mgd_types
if not self.is_stored:
offending_types -= self.smt_allow_on_create
if offending_types:
if self.handling == 'strict':
raise ServerManagedTermError(offending_types, 't')
else:
for t in offending_types:
logger.info('Removing offending type: {}'.format(t))
gr.remove((None, RDF.type, t))
#logger.debug('Sanitized graph: {}'.format(gr.serialize(
# format='turtle').decode('utf-8')))
return gr
def _add_srv_mgd_triples(self, create=False):
'''
Add server-managed triples to a provided IMR.
@param create (boolean) Whether the resource is being created.
'''
# Base LDP types.
for t in self.base_types:
self.provided_imr.add(RDF.type, t)
# Message digest.
cksum = self.tbox.rdf_cksum(self.provided_imr.graph)
self.provided_imr.set(nsc['premis'].hasMessageDigest,
URIRef('urn:sha1:{}'.format(cksum)))
# Create and modify timestamp.
if create:
self.provided_imr.set(nsc['fcrepo'].created, env.timestamp_term)
self.provided_imr.set(nsc['fcrepo'].createdBy, self.DEFAULT_USER)
else:
self.provided_imr.set(nsc['fcrepo'].created,
self.metadata.value(nsc['fcrepo'].created))
self.provided_imr.set(nsc['fcrepo'].createdBy,
self.metadata.value(nsc['fcrepo'].createdBy))
self.provided_imr.set(nsc['fcrepo'].lastModified, env.timestamp_term)
self.provided_imr.set(nsc['fcrepo'].lastModifiedBy, self.DEFAULT_USER)
def _containment_rel(self, create):
'''Find the closest parent in the path indicated by the uid and
establish a containment triple.
Check the path-wise parent of the new resource. If it exists, add the
containment relationship with this UID. Otherwise, create a container
resource as the parent.
This function may recurse up the path tree until an existing container
is found.
E.g. if only fcres:/a exists:
- If fcres:/a/b/c/d is being created, a becomes container of
fcres:/a/b/c/d. Also, containers are created for fcres:a/b and
fcres:/a/b/c.
- If fcres:/e is being created, the root node becomes container of
fcres:/e.
@param create (bool) Whether the resource is being created. If false,
the parent container is not updated.
'''
from lakesuperior.model.ldp_factory import LdpFactory
if '/' in self.uid.lstrip('/'):
# Traverse up the hierarchy to find the parent.
path_components = self.uid.lstrip('/').split('/')
cnd_parent_uid = '/' + '/'.join(path_components[:-1])
if rdfly.ask_rsrc_exists(cnd_parent_uid):
parent_rsrc = LdpFactory.from_stored(cnd_parent_uid)
if nsc['ldp'].Container not in parent_rsrc.types:
raise InvalidResourceError(
cnd_parent_uid, 'Parent {} is not a container.')
parent_uid = cnd_parent_uid
else:
parent_rsrc = LdpFactory.new_container(cnd_parent_uid)
# This will trigger this method again and recurse until an
# existing container or the root node is reached.
parent_rsrc.create_or_replace()
parent_uid = parent_rsrc.uid
else:
parent_uid = ROOT_UID
parent_rsrc = LdpFactory.from_stored(
parent_uid, repr_opts={'incl_children': False}, handling='none')
# Only update parent if the resource is new.
if create:
add_gr = Graph()
add_gr.add(
(nsc['fcres'][parent_uid], nsc['ldp'].contains, self.uri))
parent_rsrc._modify_rsrc(RES_UPDATED, add_trp=add_gr)
# Direct or indirect container relationship.
return self._add_ldp_dc_ic_rel(parent_rsrc)
def _dedup_deltas(self, remove_gr, add_gr):
'''
Remove duplicate triples from add and remove delta graphs, which would
otherwise contain unnecessary statements that annul each other.
@return tuple 2 "clean" sets of respectively remove statements and
add statements.
'''
return (remove_gr - add_gr, add_gr - remove_gr)
def _add_ldp_dc_ic_rel(self, cont_rsrc):
'''
Add relationship triples from a parent direct or indirect container.
@param cont_rsrc (rdflib.resource.Resouce) The container resource.
'''
cont_p = set(cont_rsrc.metadata.graph.predicates())
logger.info('Checking direct or indirect containment.')
logger.debug('Parent predicates: {}'.format(cont_p))
add_trp = {(self.uri, nsc['fcrepo'].hasParent, cont_rsrc.uri)}
if self.MBR_RSRC_URI in cont_p and self.MBR_REL_URI in cont_p:
from lakesuperior.model.ldp_factory import LdpFactory
s = cont_rsrc.metadata.value(self.MBR_RSRC_URI).identifier
p = cont_rsrc.metadata.value(self.MBR_REL_URI).identifier
if cont_rsrc.metadata[RDF.type:nsc['ldp'].DirectContainer]:
logger.info('Parent is a direct container.')
logger.debug('Creating DC triples.')
o = self.uri
elif (cont_rsrc.metadata[RDF.type:nsc['ldp'].IndirectContainer]
and self.INS_CNT_REL_URI in cont_p):
logger.info('Parent is an indirect container.')
cont_rel_uri = cont_rsrc.metadata.value(
self.INS_CNT_REL_URI).identifier
o = self.provided_imr.value(cont_rel_uri).identifier
logger.debug('Target URI: {}'.format(o))
logger.debug('Creating IC triples.')
target_rsrc = LdpFactory.from_stored(rdfly.uri_to_uid(s))
target_rsrc._modify_rsrc(RES_UPDATED, add_trp={(s, p, o)})
return add_trp
def _sparql_update(self, update_str, notify=True):
'''
Apply a SPARQL update to a resource.
@param update_str (string) SPARQL-Update string. All URIs are local.
@return
'''
self.handling = 'lenient' # FCREPO does that and Hyrax requires it.
delta = self._sparql_delta(update_str)
return self._modify_rsrc(RES_UPDATED, *delta, notify=notify)
def _sparql_delta(self, q):
'''
Calculate the delta obtained by a SPARQL Update operation.
This is a critical component of the SPARQL update prcess and does a
couple of things:
1. It ensures that no resources outside of the subject of the request
are modified (e.g. by variable subjects)
2. It verifies that none of the terms being modified is server managed.
This method extracts an in-memory copy of the resource and performs the
query on that once it has checked if any of the server managed terms is
in the delta. If it is, it raises an exception.
NOTE: This only checks if a server-managed term is effectively being
modified. If a server-managed term is present in the query but does not
cause any change in the updated resource, no error is raised.
@return tuple(rdflib.Graph) Remove and add graphs. These can be used
with `BaseStoreLayout.update_resource` and/or recorded as separate
events in a provenance tracking system.
'''
logger.debug('Provided SPARQL query: {}'.format(q))
pre_gr = self.imr.graph
post_gr = pre_gr | Graph()
post_gr.update(q)
remove_gr, add_gr = self._dedup_deltas(pre_gr, post_gr)
#logger.debug('Removing: {}'.format(
# remove_gr.serialize(format='turtle').decode('utf8')))
#logger.debug('Adding: {}'.format(
# add_gr.serialize(format='turtle').decode('utf8')))
remove_gr = self._check_mgd_terms(remove_gr)
add_gr = self._check_mgd_terms(add_gr)
return set(remove_gr), set(add_gr)
def get_fare(self, fare_id):
fare = Resource(self.graph, URIRef(self.uri + "fare_" + fare_id))
fare.set(RDF.type, self.GTFS.FareClass)
fare.set(DCTERMS.identifier, Literal(fare_id, datatype=XSD.string))
return fare
def convert_calendar(self, csv_filename):
read_calendar = self.__open_file(csv_filename)
for row in read_calendar:
service = self.get_service(str.strip(row["service_id"]))
calendar = Resource(self.graph, URIRef(self.uri + str.strip(row["service_id"]) + "_cal"))
service.add(self.GTFS.serviceRule, calendar)
calendar.set(RDF.type, self.GTFS.CalendarRule)
calendar.set(self.GTFS.monday, Literal(str.strip(row["monday"]), datatype=XSD.boolean))
calendar.set(self.GTFS.tuesday, Literal(str.strip(row["tuesday"]), datatype=XSD.boolean))
calendar.set(self.GTFS.wednesday, Literal(str.strip(row["wednesday"]), datatype=XSD.boolean))
calendar.set(self.GTFS.thursday, Literal(str.strip(row["thursday"]), datatype=XSD.boolean))
calendar.set(self.GTFS.friday, Literal(str.strip(row["friday"]), datatype=XSD.boolean))
calendar.set(self.GTFS.saturday, Literal(str.strip(row["saturday"]), datatype=XSD.boolean))
calendar.set(self.GTFS.sunday, Literal(str.strip(row["sunday"]), datatype=XSD.boolean))
temporal = Resource(self.graph, URIRef(self.uri + str.strip(row["service_id"]) + "_cal" + "_temporal"))
calendar.set(DCTERMS.temporal, temporal)
temporal.add(self.SCHEMA.startDate, self.get_date_literal(str.strip(row["start_date"])))
temporal.add(self.SCHEMA.endDate, self.get_date_literal(str.strip(row["end_date"])))
def add_date(self):
"""
Add vivo:DateTimeValue for publication.
:return: rdflib.Graph
"""
g = Graph()
date_uri = D['date-' + self.localid]
de = Resource(g, date_uri)
de.set(RDF.type, VIVO.DateTimeValue)
year, month, month_num = self.pub_date()
# Add year and month if possible.
if month_num is not None:
de.set(RDFS.label, Literal("{}, {}".format(month, year)))
de.set(
VIVO.dateTime,
Literal("{}-{}".format(year, month_num), datatype=XSD.dayMonth)
)
de.set(VIVO.dateTimePrecision, VIVO.yearMonthPrecision)
else:
de.set(RDFS.label, Literal(year))
de.set(
VIVO.dateTime,
Literal("{}".format(year), datatype=XSD.year)
)
de.set(VIVO.dateTimePrecision, VIVO.yearPrecision)
g.add((self.pub_uri, VIVO.dateTimeValue, date_uri))
return g
def to_rdf(self):
"""
Convert the API publication object to VIVO RDF.
:return: rdflib.Graph
"""
g = Graph()
pub = Resource(g, self.pub_uri)
pub.set(RDF.type, self.vivo_type())
pub.set(RDFS.label, Literal(self.title()))
# WoS UT. Map to VIVO.identifier for now.
# ToDo: this should be a more specific property
pub.set(VIVO.identifier, Literal(self.ut()))
# DOI
doi = self.doi()
if doi is not None:
pub.set(BIBO.doi, Literal(doi))
# Volume
volume = self.volume()
if volume is not None:
pub.set(BIBO.volume, Literal(volume))
# Issue
issue = self.issue()
if issue is not None:
pub.set(BIBO.issue, Literal(issue))
# Pages
pages = self.pages()
if pages is not None:
start, end = pages.split('-')
pub.set(BIBO.start, Literal(start))
pub.set(BIBO.end, Literal(end))
# publication venue
g += self.add_venue()
# date
g += self.add_date()
# authorship and vcards
g += self.authorship()
# links
web_link, linkg = self.add_vcard_weblink()
g += linkg
# relate web link and publication
g.add((self.pub_uri, OBO['ARG_2000028'], web_link))
return g
def get_agency(self, agency_id):
agency = Resource(self.graph, URIRef(self.uri + "agency_" + agency_id))
agency.add(RDF.type, self.GTFS.Agency)
agency.set(DCTERMS.identifier, Literal(agency_id, datatype=XSD.string))
return agency
def get_shape(self, shape_id):
shape = Resource(self.graph, URIRef(self.uri + "shape_" + shape_id))
shape.set(RDF.type, self.GTFS.Shape)
shape.set(DCTERMS.identifier, Literal(shape_id, datatype=XSD.string))
return shape
def to_rdf(self):
uri = self._uri()
g = Graph()
jr = Resource(g, uri)
jr.set(RDF.type, BIBO.Journal)
jr.set(RDFS.label, Literal(self.title))
jr.set(LOCAL.identifier, Literal(self.wosid))
if self.issn is not None:
jr.set(BIBO.issn, Literal(self.issn))
if self.eissn is not None:
jr.set(BIBO.eissn, Literal(self.eissn))
if self.wikidata is not None:
jr.set(OWL.sameAs, URIRef(self.wikidata))
return g
def process(self, input, output):
username = "******"
password = "******"
lmClient = LifemapperClient(username, password)
# Get file download URL of the TIFF layer
manif = input.value(DATA.hasManifestation)
tiffFileDownloadURL = manif.value(DATA.hasFileDownloadURL)
# Get the typeCode and layerUnits
typeCode = input.value(LM.hasTypeCode)
layerUnits = input.value(LM.hasLayerUnits)
# Get the JSON spec
jsonSpecification = input.value(LM.hasJSONExperimentSpecificationURL)
lmClient.postLayer(tiffFileDownloadURL, layerUnits, typeCode)
#layerID = str(12)
layerID = lmClient.getLayerID()
layerURL = lmClient.getLayerURL()
print "posted layer ID %s " % layerID
# The URI generator
resourceURI = ResourceURI()
# Create new manifestation
fileManifestation = RDFLibResource(output.graph, resourceURI.getURI("manifestation"))
FileManifestationClass = RDFLibResource(output.graph, DATA.FileManifestation)
fileManifestation.set(RDF.type, FileManifestationClass)
fileManifestation.set(DATA.hasLandingPageURL, Literal(layerURL))
# Create the ScenarioLayer
layer = RDFLibResource(output.graph, resourceURI.getURI("layer"))
ScenarioLayerClass = RDFLibResource(output.graph, LM.ScenarioLayer)
layer.set(RDF.type, ScenarioLayerClass)
layer.set(DATA.hasManifestation, fileManifestation)
layer.set(LM.hasLayerID, Literal(layerID))
layer.set(LM.hasLayerURL, Literal(layerURL))
layer.set(LM.hasJSONExperimentSpecificationURL, jsonSpecification)
output.set(LM.hasPublishedLayer, layer)