diff pdfextract/writeCatalogue.py @ 1:365a37a2fb6c

added files from pdfextract directory
author nothing@tehis.net
date Mon, 25 Feb 2013 14:47:41 +0000
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/pdfextract/writeCatalogue.py	Mon Feb 25 14:47:41 2013 +0000
@@ -0,0 +1,27 @@
+import rdflib, os, fnmatch, urllib2
+from rdflib import Graph, RDF, RDFS, plugin, URIRef, Literal, OWL
+from xml.dom.minidom import parseString
+
+ns = 'http://sovarr.c4dm.eecs.qmul.ac.uk/features/'
+
+basedir = '/Users/alo/MusicOntology/features/'
+
+execfile(basedir + 'pdfextract/graphDefs.py')
+
+graph = Graph()
+graph.bind('af', URIRef(ns))
+graph.bind('dc', URIRef('http://purl.org/dc/elements/1.1/'))
+graph.bind('owl', OWL)
+
+addBaseTriples(graph, ns)
+
+loadBase( graph, basedir + 'rdf/base.rdf' )
+
+for name in os.listdir(basedir+'rdf/'):
+    if fnmatch.fnmatch(name, 'af-*.rdf'):
+        addTriplesFromFile(graph, basedir+'rdf/'+name, ns)
+
+compareForSimilarities(graph, ns)
+
+graph.serialize(basedir + 'af-catalogue.rdf')
+graph.serialize(basedir + 'af-catalogue.n3', format='n3')
\ No newline at end of file