Source code for rdflib.plugins.parsers.nquads

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( == 449
>>> # There should be 16 separate contexts
>>> assert len([x for x in]) == 16
>>> # is the name of entity E10009 "Arco Publications"?
>>> #   (in graph
>>> # Looking for:
>>> # <>
>>> #   <>
>>> #   "Arco Publications"
>>> #   <>
>>> s = URIRef("")
>>> FOAF = Namespace("")
>>> assert(g.value(s,"Arco Publications"))

from codecs import getreader

from rdflib.py3compat import b

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
from rdflib.plugins.parsers.ntriples import r_wspaces

__all__ = ['NQuadsParser']

[docs]class NQuadsParser(NTriplesParser):
[docs] def parse(self, inputsource, sink, **kwargs): """Parse f as an N-Triples file.""" assert, ("NQuadsParser must be given" " a context aware store.") self.sink = ConjunctiveGraph(, 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, msg: raise ParseError("Invalid line (%s):\n%r" % (msg, __line)) return self.sink
[docs] def parseline(self): if (not self.line) or self.line.startswith(('#')): return # The line is empty or a comment subject = self.subject() predicate = self.predicate() obj = self.object() context = self.uriref() or self.nodeid() or self.sink.identifier 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))