def parse(self):
# Before we parse the RDF here, maybe we have a link to some
# other page via a link rel?
# Okay, parse the RDF
self._extractRdf()
# We go through all the RDF chunks, looking for the one
# that is about this local document, and we get all the information
# from there.
found = 0
for rdf_chunk in self.rdf_chunks:
cc_rdf= ccrdf.ccRdf()
try:
cc_rdf.parse(rdf_chunk)
except Exception, (strerror):
print "BAD PARSING: %s" % strerror
continue
# We check all the works
for work in cc_rdf.works():
# Is it about the right document?
if work.subject != "" and work.subject != self.url:
# Special case the situation where the subject is a prefix of the URL
if self.url.find(work.subject) == -1:
print "BAD SUBJECT: %s" % work.subject
continue
# Okay, we are dealing with the right thing
found = 1
# Store the cc work data structure
self.ccWork = work
def xmp(self):
"""If the XMP data has not been previously extracted or if reload is
True, scan the file for embedded XMP. If the data has been previously
extracted, just return our cached copy.
Returns XXX.
"""
if self.__xmp is None:
# scan the file for XMP
self.__xmp = ccrdf.ccRdf()
self.xmp_data = ""
file_contents = file(self.filename,'r').read()
for start_tag, end_tag in \
zip(self.START_STRINGS, self.END_STRINGS):
if file_contents.find(start_tag) == -1:
continue
# found the embedded RDF
rdf_string = file_contents[file_contents.find(start_tag):
file_contents.find(end_tag) + len(end_tag)]
# store the raw string
self.xmp_data = rdf_string
# parse the RDF
self.__xmp.parse(rdf_string)
return self.__xmp
def verify(filename):
"""Extracts license claim information from a file and verifies it.
Returns the following status codes:
1 Verified
0 No RDF
-1 Work information not found (possible SHA1 mismatch)
-2 Verification license does not match claim.
"""
status = 0
claim = metadata(filename).getClaim()
if claim is None:
raise cctag.exceptions.NotLicensedException
fileinfo = parseClaim(claim)
fileinfo['sha'] = 'urn:sha1:%s' % cctag.rdf.fileHash(filename)
verifyRdf = rdfextract.RdfExtractor().extractRdfText(
rdfextract.retrieveUrl(fileinfo['verify at'])
)
# check if we found any RDF at all, and update the status code
if len(verifyRdf) > 0:
status = -1
# check each block of RDF
# (a verification page may also have it's own license RDF embedded)
for block in verifyRdf:
# parse/validate the RDF
verifyCc = ccrdf.ccRdf()
verifyCc.parse(block)
# for each work in the RDF block...
for work in verifyCc.works():
# if the subject matches...
if work.subject == fileinfo['sha']:
# we found the work information;
# only one reason left to not verify
status = -2
# we found the work, now make sure the license matches
for license in work.licenses():
if license == fileinfo['license']:
return 1
# either the file wasn't found, or the license didn't match
return status
