1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
|
"""
This is a rdflib plugin for parsing NQuad files into Conjunctive
graphs that can be used and queried. The store that backs the graph
*must* be able to handle contexts.
>>> from rdflib import ConjunctiveGraph, URIRef, Namespace
>>> g = ConjunctiveGraph()
>>> data = open("test/nquads.rdflib/example.nquads", "rb")
>>> g.parse(data, format="nquads") # doctest:+ELLIPSIS
<Graph identifier=... (<class 'rdflib.graph.Graph'>)>
>>> assert len(g.store) == 449
>>> # There should be 16 separate contexts
>>> assert len([x for x in g.store.contexts()]) == 16
>>> # is the name of entity E10009 "Arco Publications"?
>>> # (in graph http://bibliographica.org/entity/E10009)
>>> # Looking for:
>>> # <http://bibliographica.org/entity/E10009>
>>> # <http://xmlns.com/foaf/0.1/name>
>>> # "Arco Publications"
>>> # <http://bibliographica.org/entity/E10009>
>>> s = URIRef("http://bibliographica.org/entity/E10009")
>>> FOAF = Namespace("http://xmlns.com/foaf/0.1/")
>>> assert(g.value(s, FOAF.name).eq("Arco Publications"))
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from codecs import getreader
from rdflib import ConjunctiveGraph
# Build up from the NTriples parser:
from rdflib.plugins.parsers.ntriples import NTriplesParser
from rdflib.plugins.parsers.ntriples import ParseError
from rdflib.plugins.parsers.ntriples import r_tail
from rdflib.plugins.parsers.ntriples import r_wspace
__all__ = ["NQuadsParser"]
class NQuadsParser(NTriplesParser):
def parse(self, inputsource, sink, **kwargs):
"""Parse f as an N-Triples file."""
assert sink.store.context_aware, (
"NQuadsParser must be given" " a context aware store."
)
self.sink = ConjunctiveGraph(store=sink.store, identifier=sink.identifier)
source = inputsource.getByteStream()
if not hasattr(source, "read"):
raise ParseError("Item to parse must be a file-like object.")
source = getreader("utf-8")(source)
self.file = source
self.buffer = ""
while True:
self.line = __line = self.readline()
if self.line is None:
break
try:
self.parseline()
except ParseError as msg:
raise ParseError("Invalid line (%s):\n%r" % (msg, __line))
return self.sink
def parseline(self):
self.eat(r_wspace)
if (not self.line) or self.line.startswith(("#")):
return # The line is empty or a comment
subject = self.subject()
self.eat(r_wspace)
predicate = self.predicate()
self.eat(r_wspace)
obj = self.object()
self.eat(r_wspace)
context = self.uriref() or self.nodeid() or self.sink.identifier
self.eat(r_tail)
if self.line:
raise ParseError("Trailing garbage")
# Must have a context aware store - add on a normal Graph
# discards anything where the ctx != graph.identifier
self.sink.get_context(context).add((subject, predicate, obj))
|
