removing uri in load_netcdf and prefer baseuri, fixing affected code and adding test

Author: jyucsiro

lib/bald/__init__.py

@@ -538,7 +538,7 @@ def load(afilepath):
     finally:
         f.close()
 
-def load_netcdf(afilepath, uri=None, baseuri=None):
+def load_netcdf(afilepath, baseuri=None):
     """
     Validate a file with respect to binary-array-linked-data.
     Returns a :class:`bald.validation.Validation`
@@ -588,8 +588,8 @@ def load_netcdf(afilepath, uri=None, baseuri=None):
         for k in fhandle.ncattrs():
             attrs[k] = getattr(fhandle, k)
         # It would be nice to use the URI of the file if it is known.
-        if uri is not None:
-            identity = uri
+        if baseuri is not None:
+            identity = baseuri
         else:
             identity = 'root'
         root_container = Container(identity, attrs, prefixes=prefixes,

lib/bald/tests/integration/TTL/array_reference_withbase.ttl

@@ -0,0 +1,20 @@
+@prefix bald: <http://binary-array-ld.net/latest/> .
+@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
+@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
+@prefix xml: <http://www.w3.org/XML/1998/namespace> .
+@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
+
+<http://example.org/base> a bald:Container ;
+    bald:contains <http://example.org/base/child_variable>,
+        <http://example.org/base/parent_variable> ;
+    bald:isPrefixedBy "prefix_list" .
+
+<http://example.org/base/parent_variable> a bald:Array ;
+    bald:references <http://example.org/base/child_variable> ;
+    bald:shape "(11, 17)" .
+
+<http://example.org/base/child_variable> a bald:Array,
+        bald:Reference ;
+    bald:array <http://example.org/base/child_variable> ;
+    bald:shape "(11, 17)" .
+

lib/bald/tests/integration/test_cdl_rdfgraph.py

@@ -25,6 +25,18 @@ def test_array_reference(self):
                 expected_ttl = sf.read()
             self.assertEqual(expected_ttl, ttl)
 
+    def test_array_reference_with_baseuri(self):
+        with self.temp_filename('.nc') as tfile:
+            cdl_file = os.path.join(self.cdl_path, 'array_reference.cdl')
+            subprocess.check_call(['ncgen', '-o', tfile, cdl_file])
+            root_container = bald.load_netcdf(tfile, baseuri='http://example.org/base')
+            ttl = root_container.rdfgraph().serialize(format='n3').decode("utf-8")
+            #with open(os.path.join(self.ttl_path, 'array_reference_withbase.ttl'), 'w') as sf:
+            #     sf.write(ttl)
+            with open(os.path.join(self.ttl_path, 'array_reference_withbase.ttl'), 'r') as sf:
+                expected_ttl = sf.read()
+            self.assertEqual(expected_ttl, ttl)
+
     def test_multi_array_reference(self):
         with self.temp_filename('.nc') as tfile:
             cdl_file = os.path.join(self.cdl_path, 'multi_array_reference.cdl')

nc2rdf/nc2rdf.py

@@ -6,21 +6,21 @@
 import numpy as np
 import bald
 
-def nc2rdf(ncfilename, outformat, container_uri=None, default_baseuri=None):  
+def nc2rdf(ncfilename, outformat, baseuri=None):  
     #print("nc2rdf test")
     #print(ncfile)
-    root_container = bald.load_netcdf(ncfilename, uri=container_uri, baseuri=default_baseuri)
+    root_container = bald.load_netcdf(ncfilename, baseuri=baseuri)
     ttl = root_container.rdfgraph().serialize(format=outformat).decode("utf-8")
     print(ttl)
 
-def cdl2rdf(cdl_file, outformat, container_uri=None, default_baseuri=None): 
+def cdl2rdf(cdl_file, outformat, baseuri=None): 
     #print("cdl2rdf test")
     #print(cdl_file)
     tfile, tfilename = tempfile.mkstemp('.nc')
     #print(tfilename)
     subprocess.check_call(['ncgen', '-o', tfilename, cdl_file])
 
-    nc2rdf(tfilename, outformat, container_uri=container_uri, default_baseuri=default_baseuri)
+    nc2rdf(tfilename, outformat, baseuri=baseuri)
 
     os.close(tfile)
     os.remove(tfilename)
@@ -29,7 +29,6 @@ def cdl2rdf(cdl_file, outformat, container_uri=None, default_baseuri=None):
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description='Convert netCDF metadata to RDF.')
     parser.add_argument('-o', action="store", dest="format", default='n3', help="RDF output format (n3 *default, ttl, xml)")
-    parser.add_argument('--uri', action="store", dest="uri", help="Container URI for the root of the graph")
     parser.add_argument('--baseuri', action="store", dest="baseuri", help="Base URI for the graph")
     parser.add_argument('--cdl', action="store_true", dest="isCDL", default=False, help="Flag to indicate file is CDL")
     parser.add_argument('--nc', action="store_true", dest="isNC", default=False, help="Flag to indicate file is netCDF")
@@ -38,8 +37,8 @@ def cdl2rdf(cdl_file, outformat, container_uri=None, default_baseuri=None):
     args = parser.parse_args()
 
     if(args.isCDL or args.ncfile.endswith(".cdl") or args.ncfile.endswith('.CDL')):
-        cdl2rdf(args.ncfile, args.format, container_uri=args.uri, default_baseuri=args.baseuri)
+        cdl2rdf(args.ncfile, args.format, baseuri=args.baseuri)
     elif(args.isNC or args.ncfile.endswith(".nc") or args.ncfile.endswith('.NC')):
-        nc2rdf(args.ncfile, args.format, container_uri=args.uri, default_baseuri=args.baseuri)
+        nc2rdf(args.ncfile, args.format, baseuri=args.baseuri)
     else:
         print("Unrecognised file suffix. Please indicate if CDL or NC via --cdl or --nc");