Update Automaton to build the cc keywork when running with inspirehep.

modules/harvest_tools/automaton.py

@@ -28,6 +28,10 @@ MSG_NSERT_FAIL = "Fail to insert the new record in the database."
 MSG_NO_OAI = "Reject no OAI identifier"
 MSG_WELL_FORM_OAI = "Reject OAI is not well formed"
 
+# search collection when using inspirehep
+# require for "Hal Hidden"
+REG_COLLECTION = re.compile(r"cc([A-Za-z ]+)(and|$)")
+
 
 class Automaton(object):
     """Base class to search and process publications:
@@ -299,6 +303,15 @@ class Automaton(object):
                        sf='year',  # sort by date
                        so='d')  # descending order
 
+            # handle the cc keyword (true inspirehep collection)
+            match = REG_COLLECTION.search(query)
+            if match:
+                dic["cc"] = match.group(1).strip()
+                dic["p"] = REG_COLLECTION.sub("", query).strip()
+                dic["p"] = dic["p"].replace("  ", " ")
+                if dic["p"] == "find":
+                    del dic["p"]
+
         # CERN INVENIO store
         else: