def parse_and_serialize(input_files,
input_format,
guess,
outfile,
output_format,
ns_bindings,
store_conn=STORE_CONNECTION,
store_type=STORE_TYPE):
store = plugin.get(store_type, Store)()
store.open(store_conn)
graph = Graph(store)
for prefix, uri in ns_bindings.items():
graph.namespace_manager.bind(prefix, uri, override=False)
for fpath in input_files:
use_format, kws = _format_and_kws(input_format)
if fpath == '-':
fpath = sys.stdin
elif not input_format and guess:
use_format = guess_format(fpath) or DEFAULT_INPUT_FORMAT
graph.parse(fpath, format=use_format, **kws)
if outfile:
output_format, kws = _format_and_kws(output_format)
graph.serialize(destination=outfile,
format=output_format,
base=None,
**kws)
store.rollback()
def to_rdf_etree(sources):
graph = ConjunctiveGraph()
for source in sources:
graph.load(source, format=guess_format(source))
io = StringIO()
graph.serialize(io, format="pretty-xml")
io.seek(0)
return etree.parse(io)
def parse_and_serialize(input_files, input_format, guess,
outfile, output_format, ns_bindings,
store_conn=STORE_CONNECTION, store_type=STORE_TYPE):
store = plugin.get(store_type, Store)()
store.open(store_conn)
graph = Graph(store)
for prefix, uri in ns_bindings.items():
graph.namespace_manager.bind(prefix, uri, override=False)
for fpath in input_files:
use_format, kws = _format_and_kws(input_format)
if fpath == '-':
fpath = sys.stdin
elif not input_format and guess:
use_format = guess_format(fpath) or DEFAULT_INPUT_FORMAT
graph.parse(fpath, format=use_format, **kws)
if outfile:
output_format, kws = _format_and_kws(output_format)
graph.serialize(destination=outfile, format=output_format, base=None, **kws)
store.rollback()
from rdflib.graph import ConjunctiveGraph
from oort.util.deps import json
from oort.gluon import Profile
from oort.gluon.parser import to_rdf
from oort.gluon.serializer import to_tree
if __name__ == '__main__':
from sys import argv, stdin
args = argv[1:]
fname = args.pop(0) if args else ""
profile_fname = args.pop(0) if args else None
lang = args.pop(0) if args else None
if not fname or fname.endswith('.json'):
infile = open(fname) if fname else stdin
tree = json.loads(
"".join(l for l in infile if not l.strip().startswith('//')))
graph = to_rdf(tree)
print graph.serialize(format="n3")
else:
graph = ConjunctiveGraph()
from rdfextras.tools.pathutils import guess_format
graph.parse(fname, format=guess_format(fname))
profile = Profile(json.load(open(profile_fname))
) if profile_fname else None
tree = to_tree(graph, profile, lang)
print json.dumps(tree, indent=4, separators=(',',': '), sort_keys=True,
check_circular=False)
from oort.util.deps import json
from oort.gluon import Profile
from oort.gluon.parser import to_rdf
from oort.gluon.serializer import to_tree
if __name__ == '__main__':
from sys import argv, stdin
args = argv[1:]
fname = args.pop(0) if args else ""
profile_fname = args.pop(0) if args else None
lang = args.pop(0) if args else None
if not fname or fname.endswith('.json'):
infile = open(fname) if fname else stdin
tree = json.loads("".join(l for l in infile
if not l.strip().startswith('//')))
graph = to_rdf(tree)
print graph.serialize(format="n3")
else:
graph = ConjunctiveGraph()
from rdfextras.tools.pathutils import guess_format
graph.parse(fname, format=guess_format(fname))
profile = Profile(json.load(
open(profile_fname))) if profile_fname else None
tree = to_tree(graph, profile, lang)
print json.dumps(tree,
indent=4,
separators=(',', ': '),
sort_keys=True,
check_circular=False)
if not args:
print "USAGE: %s FILE [rdf...]" % p.basename(cmd)
print "Where FILE is a local copy of <https://lagen.nu/1976:725>. Get it by doing e.g.:"
print " $ /usr/bin/curl -sk 'https://lagen.nu/1976:725' > /tmp/sfs-1976_725.xhtml"
print
print "If additional local rdf files are supplied, a diff of the " \
"extracted data and the supplied data is output (instead of just the " \
"extracted data)."
exit()
docpath = args[0]
graph = fsdoc_to_graph(docpath)
from rdfextras.tools.pathutils import guess_format
cmp_graph = Graph()
for fpath in args[1:]:
cmp_graph.load(fpath, format=guess_format(fpath))
if cmp_graph:
from rdflib.compare import graph_diff
in_both, in_first, in_second = graph_diff(graph, cmp_graph)
print "# %s new statements:" % len(in_first)
for pfx, uri in graph.namespaces():
in_first.bind(pfx, uri)
print in_first.serialize(format='n3')
else:
print "# Nothing to compare against. New RDF is:"
print graph.serialize(format='n3')
