def test_andras_loop():
manifast = \
"https://raw.githubusercontent.com/SuLab/Genewiki-ShEx/master/pathways/wikipathways/manifest_all.json"
manifest = jsonasobj.loads(requests.get(manifast).text)
for case in manifest:
print(case._as_json_dumps())
if case.data.startswith("Endpoint:"):
sparql_endpoint = case.data.replace("Endpoint: ", "")
schema = requests.get(case.schemaURL).text
shex = ShExC(schema).schema
print("==== Schema =====")
# print(shex._as_json_dumps())
evaluator = ShExEvaluator(schema=shex, debug=True)
sparql_query = case.queryMap.replace("SPARQL '''",
"").replace("'''@START", "")
df = get_sparql_dataframe(sparql_endpoint, sparql_query)
for wdid in df.item:
slurpeddata = requests.get(wdid + ".ttl")
results = evaluator.evaluate(rdf=slurpeddata.text,
focus=wdid,
debug=False)
for result in results:
if result.result:
print(str(result.focus) + ": CONFORMS")
else:
print("item with issue: " + str(result.focus) + " - " +
"shape applied: " + str(result.start))
def main(argv: Optional[List[str]] = None):
opts = genargs().parse_args(argv)
if not os.path.isdir(opts.indir):
print("Input directory {} doesn't exist".format(opts.indir),
file=sys.stderr)
sys.exit(1)
os.makedirs(opts.outdir, exist_ok=True)
conversion_count = 0
for fname in os.listdir(opts.indir):
if fname.endswith('.shexj'):
out_fname = change_suffix(fname, '.shexj', '.shexc')
try:
with open(os.path.join(opts.indir, fname)) as f:
tweaked_shex = dumps(tweak_shexj(load(f)), indent=' ')
if opts.save:
with open(
os.path.join(
opts.outdir,
change_suffix(fname, '.shexj', '.shexjt')),
'w') as outf:
outf.write(tweaked_shex)
shexc = str(ShExC(tweaked_shex))
with open(os.path.join(opts.outdir, out_fname), 'w') as of:
of.write(shexc)
conversion_count += 1
except ValueError as e:
print(f"{os.path.join(opts.indir, fname)} conversion failure")
print(str(e))
print(f"{conversion_count} files converted")
def end_schema(self, output: Optional[str]) -> None:
shex = as_json(self.shex)
if self.format == 'rdf':
g = Graph()
g.parse(data=shex, format="json-ld")
g.bind('owl', OWL)
g.bind('biolink', BIOENTITY)
g.bind('meta', META)
shex = g.serialize(format='turtle').decode()
elif self.format == 'shex':
# TODO: wait until the better ShExC emitter is committed
shex = str(ShExC(self.shex))
if output:
with open(output, 'w') as outf:
outf.write(shex)
else:
print(shex)
def end_schema(self, output: Optional[str] = None, **_) -> None:
self.shex.shapes = self.shapes if self.shapes else [Shape()]
shex = as_json(self.shex)
if self.format == 'rdf':
g = Graph()
g.parse(data=shex, format="json-ld")
g.bind('owl', OWL)
shex = g.serialize(format='turtle').decode()
elif self.format == 'shex':
g = Graph()
self.namespaces.load_graph(g)
shex = str(ShExC(self.shex, base=sfx(self.namespaces._base), namespaces=g))
if output:
with open(output, 'w') as outf:
outf.write(shex)
else:
print(shex)
def run_shex_manifest():
print(os.environ["SHEX_MANIFEST"])
manifest = jsonasobj.loads(requests.get(os.environ["SHEX_MANIFEST"]).text)
for case in manifest:
if case.data.startswith("Endpoint:"):
sparql_endpoint = case.data.replace("Endpoint: ", "")
schema = requests.get(case.schemaURL).text
shex = ShExC(schema).schema
evaluator = ShExEvaluator(schema=shex, debug=True)
sparql_query = case.queryMap.replace("SPARQL '''",
"").replace("'''@START", "")
df = wdi_core.WDItemEngine.execute_sparql_query(sparql_query)
for row in df["results"]["bindings"]:
wdid = row["item"]["value"]
slurpeddata = SlurpyGraph(sparql_endpoint)
try:
if os.environ["debug"] == "True":
debug = True
elif os.environ["debug"] == "False":
debug = False
results = evaluator.evaluate(rdf=slurpeddata,
focus=wdid,
debug=debug)
for result in results:
if result.result:
print(str(result.focus) + ": INFO")
msg = wdi_helpers.format_msg(
wdid, wdid, None, 'CONFORMS', '')
wdi_core.WDItemEngine.log("INFO", msg)
else:
msg = wdi_helpers.format_msg(
wdid, wdid, None, '', result.reason)
wdi_core.WDItemEngine.log("ERROR", msg)
except RuntimeError:
print(
"Continue after 1 minute, no validation happened on" +
wdid)
continue
def run_shex_manifest():
#manifest = \
# "https://raw.githubusercontent.com/SuLab/Genewiki-ShEx/master/pathways/wikipathways/manifest_all.json"
# manifest = jsonasobj.loads(requests.get(os.environ['MANIFEST_URL']).text)
manifest_loc = "https://raw.githubusercontent.com/SuLab/Genewiki-ShEx/master/diseases/manifest_all.json"
manifest = jsonasobj.loads(requests.get(manifest_loc).text)
# print(os.environ['MANIFEST_URL'])
for case in manifest:
print(case._as_json_dumps())
if case.data.startswith("Endpoint:"):
sparql_endpoint = case.data.replace("Endpoint: ", "")
schema = requests.get(case.schemaURL).text
shex = ShExC(schema).schema
# print("==== Schema =====")
#print(shex._as_json_dumps())
evaluator = ShExEvaluator(schema=shex, debug=False)
sparql_query = case.queryMap.replace("SPARQL '''", "").replace("'''@START", "")
df = get_sparql_dataframe(sparql_endpoint, sparql_query)
for wdid in df.item:
slurpeddata = SlurpyGraph(sparql_endpoint)
# slurpeddata = requests.get(wdid + ".ttl")
results = evaluator.evaluate(rdf=slurpeddata, focus=wdid, debug=False, debug_slurps=True)
for result in results:
if result.result:
print(str(result.focus) + ": CONFORMS")
else:
if str(result.focus) in [
"http://www.wikidata.org/entity/Q33525",
"http://www.wikidata.org/entity/Q62736",
"http://www.wikidata.org/entity/Q112670"
]:
continue
print(
"item with issue: " + str(result.focus) + " - " + "shape applied: " + str(result.start))
# run_shex_manifest()
def run_shex_manifest():
manifest = jsonasobj.loads(
requests.get(
"https://raw.githubusercontent.com/SuLab/Genewiki-ShEx/master/pathways/reactome/manifest.json"
).text)
for case in manifest:
if case.data.startswith("Endpoint:"):
sparql_endpoint = case.data.replace("Endpoint: ", "")
schema = requests.get(case.schemaURL).text
shex = ShExC(schema).schema
evaluator = ShExEvaluator(schema=shex, debug=True)
sparql_query = case.queryMap.replace("SPARQL '''",
"").replace("'''@START", "")
df = wdi_core.WDItemEngine.execute_sparql_query(sparql_query)
for row in df["results"]["bindings"]:
wdid = row["item"]["value"]
slurpeddata = SlurpyGraph(sparql_endpoint)
try:
results = evaluator.evaluate(rdf=slurpeddata,
focus=wdid,
debug=False)
for result in results:
if result.result:
print(str(result.focus) + ": INFO")
msg = wdi_helpers.format_msg(
wdid, wdid, None, 'CONFORMS', '')
wdi_core.WDItemEngine.log("INFO", msg)
else:
msg = wdi_helpers.format_msg(
wdid, wdid, None, '', '')
wdi_core.WDItemEngine.log("ERROR", s)
except RuntimeError:
print(
"Continue after 1 minute, no validation happened on" +
wdid)
continue
def schema(self) -> Optional[str]:
"""
:return: The ShExC representation of the schema if one is supplied
"""
return str(ShExC(self._schema)) if self._schema else None
