clean extract function

atomrdf/graph.py

@@ -1161,7 +1161,7 @@ def activity_ids(self):
 
         return [x[0] for x in self.triples((None, RDF.type, PROV.Activity))]
 
-    def iterate_graph(self, item, create_new_graph=False):
+    def iterate_graph(self, item, create_new_graph=False, create_new_list=False):
         """
         Iterate through the graph starting from the given item.
 
@@ -1177,16 +1177,40 @@ def iterate_graph(self, item, create_new_graph=False):
         -------
         None
         """
-        if isinstance(item, str):
-            item = URIRef(item)
+        #active = False
+
+        if not type(item).__name__ == 'URIRef':
+            return
+
+        #if create_new_graph:
+        #    self.sgraph = KnowledgeGraph()
+
+        if create_new_list:
+            self.slist = []
 
-        if create_new_graph:
-            self.sgraph = KnowledgeGraph()
         triples = list(self.triples((item, None, None)))
+        #print(triples)
+
         for triple in triples:
-            self.sgraph.graph.add(triple)
+            #active = True
+            #if create_new_graph:
+            #    self.sgraph.graph.add(triple)
+            self.slist.append(triple)
             self.iterate_graph(triple[2])
-
+
+    def iterate_and_reapply_triples(self, item):
+        self.iterate_graph(item, create_new_list=True)
+        triples = copy.deepcopy(self.slist)
+        #now we have to edit this triples, and reapply them
+        #for that we make a dict of all URIRef values in this graph
+        uri_dict = {}
+        for triple in triples:
+            if isinstance(triple[0], URIRef):
+                print(triple[0])
+                if triple[0].toPython() not in uri_dict.keys():
+                    uri_dict[triple[0].toPython()] = None
+        return uri_dict
+
     def get_sample(self, sample, no_atoms=False):
         """
         Get the Sample as a KnowledgeGraph
@@ -1210,7 +1234,7 @@ def get_sample(self, sample, no_atoms=False):
         if isinstance(sample, str):
             sample = URIRef(sample)
 
-        self.iterate_graph(sample, create_new_graph=True)
+        _ = self.iterate_graph(sample, create_new_graph=True)
         if no_atoms:
             na = self.sgraph.value(sample, CMSO.hasNumberOfAtoms).toPython()
             return self.sgraph, na

atomrdf/structure.py

@@ -2553,3 +2553,18 @@ def add_shear_triples(self, translation_vector, plane, distance, ):
             self.graph.add((plane_vector, CMSO.hasComponent_y, Literal(plane[1], datatype=XSD.float),))
             self.graph.add((plane_vector, CMSO.hasComponent_z, Literal(plane[2], datatype=XSD.float),))
             self.graph.add((activity, UNSAFECMSO.hasDistance, Literal(distance, datatype=XSD.float)))
+
+    def copy_defects(self, parent_sample):
+        if self.sample is None:
+            return
+        if parent_sample is None:
+            return
+
+        parent_material = list([k[2] for k in self.kg.triples((parent_sample, CMSO.hasMaterial, None))])[0]
+        parent_defects = list([x[2] for x in self.kg.triples((parent_material, CMSO.hasDefect, None))])
+
+        material = list([k[2] for k in self.kg.triples((self.sample, CMSO.hasMaterial, None))])[0]
+
+        for defect in parent_defects:
+            new_defect = URIRef(defect.toPython())
+

examples/02_grain_boundaries.ipynb

@@ -60,6 +60,78 @@
     "                        graph=kg)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "dc65fb07",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from atomrdf.namespace import PROV, CMSO\n",
+    "parent_material = list(\n",
+    "    [\n",
+    "        k[2]\n",
+    "        for k in kg.triples((struct_gb_1.sample, CMSO.hasMaterial, None))\n",
+    "    ]\n",
+    ")[0]\n",
+    "parent_defects = list(\n",
+    "    [x[2] for x in kg.triples((parent_material, CMSO.hasDefect, None))]\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "2f07ae38",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[rdflib.term.URIRef('sample:ddb98ea8-c0dd-4b86-b6a1-97bddf93b94a_SymmetricalTiltGrainBoundary')]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "parent_defects"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "6f2b8588",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "sample:ddb98ea8-c0dd-4b86-b6a1-97bddf93b94a_SymmetricalTiltGrainBoundary\n",
+      "sample:ddb98ea8-c0dd-4b86-b6a1-97bddf93b94a_SymmetricalTiltGrainBoundary\n",
+      "sample:ddb98ea8-c0dd-4b86-b6a1-97bddf93b94a_SymmetricalTiltGrainBoundary\n",
+      "sample:ddb98ea8-c0dd-4b86-b6a1-97bddf93b94a_SymmetricalTiltGrainBoundary\n",
+      "sample:ddb98ea8-c0dd-4b86-b6a1-97bddf93b94a_SymmetricalTiltGrainBoundary\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'sample:ddb98ea8-c0dd-4b86-b6a1-97bddf93b94a_SymmetricalTiltGrainBoundary': None}"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kg.iterate_and_reapply_triples(parent_defects[0])"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "717626e5-3672-470e-a9d9-2878310268ca",