def _load_all_graphs(self, progress, trip_prog):
import transaction
from rdflib import plugin
from rdflib.parser import Parser, create_input_source
idx_fname = pth_join(self.powdir, 'graphs', 'index')
triples_read = 0
if exists(idx_fname):
dest = self._conf()['rdf.graph']
with open(idx_fname) as index_file:
cnt = 0
for l in index_file:
cnt += 1
index_file.seek(0)
progress.total = cnt
with transaction.manager:
for l in index_file:
fname, ctx = l.strip().split(' ')
parser = plugin.get('nt', Parser)()
with open(pth_join(self.powdir, 'graphs', fname), 'rb') as f, \
_BatchAddGraph(dest.get_context(ctx), batchsize=4000) as g:
parser.parse(create_input_source(f), g)
progress.update(1)
triples_read += g.count
trip_prog.update(g.count)
progress.write('Finalizing writes to database...')
progress.write('Loaded {:,} triples'.format(triples_read))
def _load_all_graphs(self, progress, trip_prog):
import transaction
from rdflib import plugin
from rdflib.parser import Parser, create_input_source
idx_fname = pth_join(self.powdir, 'graphs', 'index')
triples_read = 0
if exists(idx_fname):
dest = self._conf()['rdf.graph']
with open(idx_fname) as index_file:
cnt = 0
for l in index_file:
cnt += 1
index_file.seek(0)
progress.total = cnt
with transaction.manager:
for l in index_file:
fname, ctx = l.strip().split(' ')
parser = plugin.get('nt', Parser)()
with open(pth_join(self.powdir, 'graphs', fname), 'rb') as f, \
_BatchAddGraph(dest.get_context(ctx), batchsize=4000) as g:
parser.parse(create_input_source(f), g)
progress.update(1)
triples_read += g.count
trip_prog.update(g.count)
progress.write('Finalizing writes to database...')
progress.write('Loaded {:,} triples'.format(triples_read))
def load(self, url):
src = VOCAB_SOURCE_MAP.get(str(url), url)
if os.path.isfile(url):
context_id = create_input_source(url).getPublicId()
last_vocab_mtime = self.mtime_map.get(url)
vocab_mtime = os.stat(url).st_mtime
if not last_vocab_mtime or last_vocab_mtime < vocab_mtime:
logger.debug("Parse file: '%s'", url)
self.mtime_map[url] = vocab_mtime
# use CG as workaround for json-ld always loading as dataset
graph = ConjunctiveGraph()
graph.parse(src, format=guess_format(src))
self.graph.remove_context(context_id)
for s, p, o in graph:
self.graph.add((s, p, o, context_id))
return graph
else:
context_id = url
if any(self.graph.triples((None, None, None), context=context_id)):
logger.debug("Using context <%s>" % context_id)
return self.graph.get_context(context_id)
cache_path = self.get_fs_path(url)
if os.path.exists(cache_path):
logger.debug("Load local copy of <%s> from '%s'", context_id, cache_path)
return self.graph.parse(cache_path, format='turtle', publicID=context_id)
else:
logger.debug("Fetching <%s> to '%s'", context_id, cache_path)
graph = self.graph.parse(src,
format='rdfa' if url.endswith('html') else None)
with open(cache_path, 'w') as f:
graph.serialize(f, format='turtle')
return graph
def run_tc(tc):
parser = RDFaParser()
graph = Graph()
source = create_input_source(cached_file(tc.html_url), publicID=tc.html_url)
parser.parse(source, graph)
sparql = open(cached_file(tc.sparql_url)).read()
ok = verify_ask(sparql, graph, tc.expected)
return ok, sparql, graph
def source_to_json(source):
# TODO: conneg for JSON (fix support in rdflib's URLInputSource!)
source = create_input_source(source)
stream=source.getByteStream()
try:
return json.load(stream)
finally:
stream.close()
def source_to_json(source):
# TODO: conneg for JSON (fix support in rdflib's URLInputSource!)
source = create_input_source(source)
stream = source.getByteStream()
try:
return json.load(stream)
finally:
stream.close()
def source_to_json(source):
# TODO: conneg for JSON (fix support in rdflib's URLInputSource!)
source = create_input_source(source, format="json-ld")
stream = source.getByteStream()
try:
return json.load(StringIO(stream.read().decode("utf-8")))
finally:
stream.close()
def source_to_json(source):
# TODO: conneg for JSON (fix support in rdflib's URLInputSource!)
source = create_input_source(source)
stream = source.getByteStream()
try:
if PY3:
return json.load(StringIO(stream.read().decode('utf-8')))
else:
return json.load(stream)
finally:
stream.close()
def source_to_json(source):
# TODO: conneg for JSON (fix support in rdflib's URLInputSource!)
source = create_input_source(source, format='json-ld')
stream = source.getByteStream()
try:
if PY3:
return json.load(StringIO(stream.read().decode('utf-8')))
else:
return json.load(stream)
finally:
stream.close()
def compile_stage5(g, docs, **kw):
"""
Derive initialisation for genetic circuits present
in the model
"""
model, _, _ = get_one(g, (None, RDF["type"], RBMO["Model"]))
for _, _, inc in g.triples((model, RBMC["include"], None)):
logging.info("stage5: including %s" % inc)
fp = create_input_source(inc.toPython()).getByteStream()
doc = fp.read()
fp.close()
docs.insert(0, doc)
return docs
def iter(self, inputsource):
"""Iter f as an N-Quads file."""
inputsource = create_input_source(source=inputsource, format='nquads')
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
self.eat(r_wspace)
if (not self.line) or self.line.startswith(('#')):
continue # The line is empty or a comment
try:
yield self.parseline()
except ParseError as msg:
raise ParseError("Invalid line (%s):\n%r" % (msg, __line))
def iter(self, inputsource):
"""Iter f as an N-Quads file."""
inputsource = create_input_source(source=inputsource, format='nquads')
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
self.eat(r_wspace)
if (not self.line) or self.line.startswith(('#')):
continue # The line is empty or a comment
try:
yield self.parseline()
except ParseError as msg:
raise ParseError("Invalid line (%s):\n%r" % (msg, __line))
def parse(self, source=None, publicID=None, format="xml", location=None, file=None, data=None, **args):
"""
Parse source adding the resulting triples to it's own context
(sub graph of this graph).
See `rdflib.graph.Graph.parse` for documentation on arguments.
:Returns:
The graph into which the source was parsed. In the case of n3
it returns the root context.
"""
source = create_input_source(source=source, publicID=publicID, location=location, file=file, data=data)
# id = self.context_id(self.absolutize(source.getPublicId()))
context = Graph(store=self.store, identifier=publicID and URIRef(publicID) or source.getPublicId())
context.remove((None, None, None))
context.parse(source, publicID=publicID, format=format, location=location, file=file, data=data, **args)
return context
def source_to_json(source):
if isinstance(source, PythonInputSource):
return source.data
if isinstance(source, StringInputSource):
return json.load(source.getCharacterStream())
# TODO: conneg for JSON (fix support in rdflib's URLInputSource!)
source = create_input_source(source, format="json-ld")
stream = source.getByteStream()
try:
# Use character stream as-is, or interpret byte stream as UTF-8
if isinstance(stream, TextIOBase):
use_stream = stream
else:
use_stream = TextIOWrapper(stream, encoding='utf-8')
return json.load(use_stream)
finally:
stream.close()
def parse(self,
source=None,
publicID=None,
format="xml",
location=None,
file=None,
data=None,
**args):
"""
Parse source adding the resulting triples to it's own context
(sub graph of this graph).
See `rdflib.graph.Graph.parse` for documentation on arguments.
:Returns:
The graph into which the source was parsed. In the case of n3
it returns the root context.
"""
source = create_input_source(source=source,
publicID=publicID,
location=location,
file=file,
data=data,
format=format)
#id = self.context_id(self.absolutize(source.getPublicId()))
context = Graph(store=self.store,
identifier=publicID and URIRef(publicID)
or source.getPublicId())
context.remove((None, None, None))
context.parse(source,
publicID=publicID,
format=format,
location=location,
file=file,
data=data,
**args)
return context
def addNQ(self, quadio):
sink = QuadSink(self)
nqp = NQuadsParser(sink)
nqp.parse(create_input_source(quadio), sink)
sink.store.finalise()
def processRequest(self):
"""Interpret a request, relay to further processing and prepare response headers."""
global debug
if "rdf-translator-dev" in self.request.url:
debug = True
if self.html == True:
self.do_pygmentize = True
self.response.headers['Content-Type'] = "text/html"
else:
if self.target_format == "pretty-xml" or self.target_format == "xml":
self.response.headers['Content-Type'] = "application/rdf+xml"
elif self.target_format == "n3":
self.response.headers['Content-Type'] = "text/n3"
elif self.target_format == "turtle":
self.response.headers['Content-Type'] = "text/turtle"
elif self.target_format == "nquads":
self.response.headers['Content-Type'] = "text/x-nquads"
elif self.target_format == "nt":
self.response.headers['Content-Type'] = "text/plain"
elif self.target_format == "trix":
self.response.headers['Content-Type'] = "application/xml"
elif self.target_format == "rdf-json" or self.target_format == "rdf-json-pretty":
self.response.headers['Content-Type'] = "application/json"
elif self.target_format == "json-ld":
self.response.headers['Content-Type'] = "application/ld+json"
elif self.target_format == "rdfa" or self.target_format == "microdata":
self.response.headers['Content-Type'] = "text/html"
else:
self.response.headers['Content-Type'] = "text/plain"
if not self.source_format or self.source_format == "detect":
if self.content:
source = create_input_source(data=self.content,
format=self.source_format)
self.source_format = source.content_type
elif self.page:
source = create_input_source(location=self.page,
format=self.source_format)
self.source_format = source.content_type
if self.source_format == "text/html":
self.source_format = "rdfa" # microdata is fallback
try:
self.response_string = "<p style='color: red; font-weight: bold; padding-top: 12px'>Translation failed</p>"
if self.content:
self.response_string = translator.convert(
self.content,
do_pygmentize=self.do_pygmentize,
file_format="string",
source_format=self.source_format,
target_format=self.target_format)
if self.response_string.strip(
) == "" and self.source_format == "rdfa": # fix microdata test
self.response_string = translator.convert(
self.content,
do_pygmentize=self.do_pygmentize,
file_format="string",
source_format="microdata",
target_format=self.target_format)
elif self.page:
self.response_string = translator.convert(
self.page,
do_pygmentize=self.do_pygmentize,
file_format="file",
source_format=self.source_format,
target_format=self.target_format)
if self.response_string.strip(
) == "" and self.source_format == "rdfa": # fix microdata test
self.response_string = translator.convert(
self.page,
do_pygmentize=self.do_pygmentize,
file_format="file",
source_format="microdata",
target_format=self.target_format)
if self.response_string.strip() == "":
raise Exception("empty result returned")
except Exception, e:
self.response.set_status(500)
if debug:
tb = traceback.format_exc()
e = "<pre style=\"color: red\">" + tb + "</pre>"
else:
e = "<pre style=\"color: red\">" + str(e) + "</pre>"
error_message = "No error message available"
if str(e).strip() != "":
error_message = "Error message:<br>%s" % str(e)
self.response_string = "<p style='color: red; font-weight: bold; padding-top: 12px'>Could not convert from %s to %s for provided resource...<br><br>%s</p>" % (
self.source_format, self.target_format, error_message)
def processRequest(self):
"""Interpret a request, relay to further processing and prepare response headers."""
global debug
if "rdf-translator-dev" in self.request.url:
debug = True
if self.html == True:
self.do_pygmentize = True
self.response.headers['Content-Type'] = "text/html"
else:
if self.target_format == "pretty-xml" or self.target_format == "xml":
self.response.headers['Content-Type'] = "application/rdf+xml"
elif self.target_format == "n3":
self.response.headers['Content-Type'] = "text/n3"
elif self.target_format == "turtle":
self.response.headers['Content-Type'] = "text/turtle"
elif self.target_format == "nquads":
self.response.headers['Content-Type'] = "text/x-nquads"
elif self.target_format == "nt":
self.response.headers['Content-Type'] = "text/plain"
elif self.target_format == "trix":
self.response.headers['Content-Type'] = "application/xml"
elif self.target_format == "rdf-json" or self.target_format == "rdf-json-pretty":
self.response.headers['Content-Type'] = "application/json"
elif self.target_format == "json-ld":
self.response.headers['Content-Type'] = "application/ld+json"
elif self.target_format == "rdfa" or self.target_format == "microdata":
self.response.headers['Content-Type'] = "text/html"
else:
self.response.headers['Content-Type'] = "text/plain"
if not self.source_format or self.source_format == "detect":
if self.content:
source = create_input_source(data=self.content, format=self.source_format)
self.source_format = source.content_type
elif self.page:
source = create_input_source(location=self.page, format=self.source_format)
self.source_format = source.content_type
if self.source_format == "text/html":
self.source_format = "rdfa" # microdata is fallback
try:
self.response_string = "<p style='color: red; font-weight: bold; padding-top: 12px'>Translation failed</p>"
if self.content:
self.response_string = translator.convert(self.content, do_pygmentize=self.do_pygmentize, file_format="string", source_format=self.source_format, target_format=self.target_format)
if self.response_string.strip() == "" and self.source_format == "rdfa": # fix microdata test
self.response_string = translator.convert(self.content, do_pygmentize=self.do_pygmentize, file_format="string", source_format="microdata", target_format=self.target_format)
elif self.page:
self.response_string = translator.convert(self.page, do_pygmentize=self.do_pygmentize, file_format="file", source_format=self.source_format, target_format=self.target_format)
if self.response_string.strip() == "" and self.source_format == "rdfa": # fix microdata test
self.response_string = translator.convert(self.page, do_pygmentize=self.do_pygmentize, file_format="file", source_format="microdata", target_format=self.target_format)
if self.response_string.strip() == "":
raise Exception("empty result returned")
except Exception, e:
self.response.set_status(500)
if debug:
tb = traceback.format_exc()
e = "<pre style=\"color: red\">"+tb+"</pre>"
else:
e = "<pre style=\"color: red\">"+str(e)+"</pre>"
error_message = "No error message available"
if str(e).strip() != "":
error_message = "Error message:<br>%s" % str(e)
self.response_string = "<p style='color: red; font-weight: bold; padding-top: 12px'>Could not convert from %s to %s for provided resource...<br><br>%s</p>" % (self.source_format, self.target_format, error_message)
def parse(self, source=None, publicID=None, format=None,
location=None, file=None, data=None, **args):
"""
Parse source adding the resulting triples to the Graph.
The source is specified using one of source, location, file or
data.
:Parameters: - `source`: An InputSource, file-like object, or string. In the case of a string the string is the location of the source.
- `location`: A string indicating the relative or absolute URL of the source. Graph's absolutize method is used if a relative location is specified.
- `file`: A file-like object.
- `data`: A string containing the data to be parsed.
- `format`: Used if format can not be determined from source. Defaults to rdf/xml.
- `publicID`: the logical URI to use as the document base. If None specified the document location is used (at least in the case where there is a document location).
:Returns:
self, the graph instance.
Examples:
>>> my_data = '''
... <rdf:RDF
... xmlns:rdf='http://www.w3.org/1999/02/22-rdf-syntax-ns#'
... xmlns:rdfs='http://www.w3.org/2000/01/rdf-schema#'
... >
... <rdf:Description>
... <rdfs:label>Example</rdfs:label>
... <rdfs:comment>This is really just an example.</rdfs:comment>
... </rdf:Description>
... </rdf:RDF>
... '''
>>> import tempfile
>>> file_name = tempfile.mktemp()
>>> f = file(file_name, "w")
>>> f.write(my_data)
>>> f.close()
>>> g = Graph()
>>> result = g.parse(data=my_data, format="application/rdf+xml")
>>> len(g)
2
>>> g = Graph()
>>> result = g.parse(location=file_name, format="application/rdf+xml")
>>> len(g)
2
>>> g = Graph()
>>> result = g.parse(file=file(file_name, "r"), format="application/rdf+xml")
>>> len(g)
2
"""
if format=="xml":
# warn... backward compat.
format = "application/rdf+xml"
source = create_input_source(source=source, publicID=publicID, location=location, file=file, data=data, format=format)
if format is None:
format = source.content_type
if format is None:
#raise Exception("Could not determin format for %r. You can expicitly specify one with the format argument." % source)
format = "application/rdf+xml"
parser = plugin.get(format, Parser)()
parser.parse(source, self, **args)
return self
def parse(self,
source=None,
publicID=None,
format=None,
location=None,
file=None,
data=None,
**args):
"""
Parse source adding the resulting triples to the Graph.
The source is specified using one of source, location, file or
data.
:Parameters: - `source`: An InputSource, file-like object, or string. In the case of a string the string is the location of the source.
- `location`: A string indicating the relative or absolute URL of the source. Graph's absolutize method is used if a relative location is specified.
- `file`: A file-like object.
- `data`: A string containing the data to be parsed.
- `format`: Used if format can not be determined from source. Defaults to rdf/xml.
- `publicID`: the logical URI to use as the document base. If None specified the document location is used (at least in the case where there is a document location).
:Returns:
self, the graph instance.
Examples:
>>> my_data = '''
... <rdf:RDF
... xmlns:rdf='http://www.w3.org/1999/02/22-rdf-syntax-ns#'
... xmlns:rdfs='http://www.w3.org/2000/01/rdf-schema#'
... >
... <rdf:Description>
... <rdfs:label>Example</rdfs:label>
... <rdfs:comment>This is really just an example.</rdfs:comment>
... </rdf:Description>
... </rdf:RDF>
... '''
>>> import tempfile
>>> file_name = tempfile.mktemp()
>>> f = file(file_name, "w")
>>> f.write(my_data)
>>> f.close()
>>> g = Graph()
>>> result = g.parse(data=my_data, format="application/rdf+xml")
>>> len(g)
2
>>> g = Graph()
>>> result = g.parse(location=file_name, format="application/rdf+xml")
>>> len(g)
2
>>> g = Graph()
>>> result = g.parse(file=file(file_name, "r"), format="application/rdf+xml")
>>> len(g)
2
"""
if format == "xml":
# warn... backward compat.
format = "application/rdf+xml"
source = create_input_source(source=source,
publicID=publicID,
location=location,
file=file,
data=data,
format=format)
if format is None:
format = source.content_type
if format is None:
#raise Exception("Could not determin format for %r. You can expicitly specify one with the format argument." % source)
format = "application/rdf+xml"
parser = plugin.get(format, Parser)()
parser.parse(source, self, **args)
return self
def read_canonical_from_file(ctx, dest, graph_fname):
bag = BatchAddGraph(dest, batchsize=10000)
parser = plugin.get('nt', Parser)()
with open(graph_fname, 'rb') as f, bag.get_context(ctx) as g:
parser.parse(create_input_source(f), g)
