more parsing of headers

src/caosadvancedtools/cfood.py

@@ -56,10 +56,11 @@ class AbstractCFood(object):
         self.use_cache = use_cache
 
     def treat_match(self, crawled_file, match):
+        print(crawled_file)
+
         entities = self.create_identifiables(crawled_file, match)
 
         for key, identifiable in entities.items():
-            print(identifiable)
 
             if identifiable is None:
                 print("THIS IS STRANGE")
@@ -70,19 +71,11 @@ class AbstractCFood(object):
             if self.use_cache:
                 identifiable_cache = Cache()
                 identifier = Cache.hash_entity(identifiable)
-                print("look for '{}' in Cache".format(identifiable.get_parents()[0]))
-                print(identifiable)
                 cached_id = identifiable_cache.check_existing(identifier)
 
                 if cached_id is not None:
-                    print(cached_id)
-                    print("found Entity '{}' in Cache".format(
-                        identifiable.get_parents()[0]))
                     existing = db.execute_query("FIND {}".format(cached_id),
                                                 unique=True)
-                else:
-                    print("did not found Entity '{}' in Cache".format(
-                        identifiable.get_parents()[0]))
 
             # Nothing in cache or cache not used. Check in CaosDB
 
@@ -92,12 +85,9 @@ class AbstractCFood(object):
             # No record matching the identifiable was found. Insert the record
 
             if existing is None:
-                print(key, "does not exist")
                 identifiable.insert()
-                print(key, "inserted")
                 entities[key] = identifiable
             else:
-                print(key, "exists")
                 entities[key] = existing
 
         if self.use_cache and cached_id is None:

src/caosadvancedtools/read_md_header.py

@@ -28,6 +28,7 @@
 import os
 import re
 
+import caosdb as db
 import yaml
 
 TEMPLATEHEADER = """
@@ -193,3 +194,35 @@ def _add_header(filename):
     with open(filename, "w") as f:
         f.write(localheader)
         f.writelines(textlines)
+
+
+def parse_responsibles(header):
+    people = []
+    for person in header["responsible"]:
+        firstname = person.split(" ")[0]
+        lastname = person.split(" ")[1]
+        p = db.Record()
+        p.add_parent("Person")
+        p.add_property("lastname", lastname)
+        p.add_property("firstname", firstname)
+        people.append(p)
+
+    return people
+
+
+def reference_data_files(entity, header):
+    for glob in header["data"]:
+        for dfile in find_file_for_fileglob(glob):
+            entity.add_property("data", dfile)
+
+
+def find_file_for_fileglob(glob):
+    # TODO this probalby needs to be extended for different kinds of glob
+    res = db.execute_query("FIND file which is stored at {}".format(glob))
+
+
+def find_records_referencing_files(glob):
+    # is it possible to reference the "data records"? anything might
+    # reference this file
+    db.execute_query("FIND Record which references file which is stored
+                     at")