version bump, renamed RML maps

Author: jermnelson

.gitignore

@@ -7,6 +7,7 @@
 *.pyc
 *eggs*
 *coverage
+logs*
 data*
 build*
 dist*

bibcat/ingesters/oai_pmh.py

@@ -6,6 +6,7 @@
 import io
 import logging
 import os
+import time
 try:
     from lxml import etree
 except ImportError:
@@ -388,6 +389,9 @@ def harvest(self, **kwargs):
             if deduplicator:
                 deduplicator.run(self.processor.output,
                     kwargs.get("dedup_classes"))
+            logging.info(" processed {}, triples count {:,}".format(
+                item_url, 
+                len(self.processor.output)))
             self.repo_graph += self.processor.output
         if 'out_file' in kwargs:
             with open(kwargs.get('out_file'), 'wb+') as fo:

bibcat/maps/bibcat-bf-batch-to-schema.ttl bibcat/maps/bf-batch-to-schema.ttl

@@ -640,4 +640,12 @@ bc:MODS2BIBFRAME_Item a rr:TriplesMap ;
         rr:objectMap [
             rr:reference "mods:originInfo/mods:dateIssued"
         ]
+    ] ;
+
+   rr:predicateObjectMap [
+        rr:predicate rdf:type ;
+        rr:objectMap [
+            rr:reference """mods:physicalDescription/mods:form[text()="image/tiff"]""" ;
+            rr:constant bf:StillImage 
+        ]
     ] .

bibcat/maps/bibcat-bf-to-schema.ttl bibcat/maps/bf-to-schema.ttl

@@ -891,18 +891,26 @@ class SPARQLBatchProcessor(Processor):
     in an attempt to reduce the time spent in the triplestore/network
     bottleneck"""
 
-    def __init__(self, rml_rules, triplestore_url):
+    def __init__(self, rml_rules, triplestore_url=None, triplestore=None):
         super(SPARQLBatchProcessor, self).__init__(rml_rules)
         __set_prefix__()
-        self.triplestore_url = triplestore_url
+        if triplestore_url is not None:
+            self.triplestore_url = triplestore_url
+        elif triplestore is not None:
+            self.triplestore = triplestore
 
     def __get_bindings__(self, sparql):
-        result = requests.post(
-            self.triplestore_url,
-            data={"query": sparql,
-                  "format": "json"})
-        bindings = result.json().get("results").get("bindings")
-            
+        bindings = []
+        if self.triplestore_url is not None:
+            result = requests.post(
+                self.triplestore_url,
+                data={"query": sparql,
+                      "format": "json"})
+            bindings = result.json().get("results").get("bindings")
+        elif self.triplestore is not None:
+            result = self.triplestore.query(sparql)
+            bindings = result.bindings
+        
         return bindings
 
     def __construct_compound_query__(self, triple_map):
@@ -941,11 +949,14 @@ def execute(self, triple_map, **kwargs):
         iterator = str(triple_map.logicalSource.iterator)
         for binding in bindings:
             entity_dict = binding.get(iterator)
-            raw_value = entity_dict.get('value')
-            if entity_dict.get('type').startswith('bnode'):
-                entity = rdflib.BNode(raw_value)
-            else:
-                entity = rdflib.URIRef(raw_value)
+            if isinstance(entity_dict, rdflib.term.Node):
+                entity = entity_dict
+            elif isinstance(entity_dict, dict):
+                raw_value = entity_dict.get('value')
+                if entity_dict.get('type').startswith('bnode'):
+                    entity = rdflib.BNode(raw_value)
+                else:
+                    entity = rdflib.URIRef(raw_value)
             if triple_map.subjectMap.class_ is not None:
                 self.output.add(
                     (entity,

bibcat/maps/bibcat-loc-bf-to-lean-bf.ttl bibcat/maps/loc-bf-to-lean-bf.ttl

@@ -6,7 +6,7 @@
 
 setup(
     name="bibcat",
-    version="1.16.2",
+    version="1.18.0",
     description="BIBCAT RDF Framework Application",
     author="KnowledgeLinks",
     author_email="knowledgelinks.io@gmail.com",