added state_territory; minor fix to related_entries; delete obj if ex…

…isting during upload

src/pyamsd/commands/to_csv.py

@@ -34,6 +34,7 @@ def run(args):
         'linked_filenames': {},
         'item_type': {},
         'item_subtype': {},
+        'state_territory': {},
         'cultural_region': {},
         'material': {},
         'technique': {},
@@ -91,6 +92,7 @@ def run(args):
                         col_name = fields[j][2]
                         if col_name in ['related_entries', 'irn']:
                             a = map(str.strip, re.split(fields[j][3], col))
+                            a = [x for x in a if x.strip()]
                             data.append(';'.join(a))
                         else:
                             print('Check init of field {}\n').format(col_name)
@@ -158,15 +160,16 @@ def run(args):
 
     # check related_entries
     for i, s in enumerate(csv_dataframe['sticks']):
-        if i > 0 and s[42].strip():
-            rids = s[42].split(';')
+        if i > 0 and s[43].strip():
+            rids = s[43].split(';')
+            # rids = [s.strip() for s in rids]
             for rid in rids:
                 if rid not in unique_ids_check:
-                    print('Related entry ID {} in line {} not found as AMSD ID\n'.format(rid, i+1))
+                    print('Related entry ID ::{}:: in line {} not found as AMSD ID\n'.format(rid, i+1))
                 if rid == s[1]:
-                    print('Related entry ID {} in line {} refers to itself\n'.format(rid, i+1))
+                    print('Related entry ID ::{}:: in line {} refers to itself\n'.format(rid, i+1))
                 if rid in unclear_ids:
-                    print('Related entry ID {} in line {} is marked as occurring more than once\n'.format(rid, i+1))
+                    print('Related entry ID ::{}:: in line {} is marked as occurring more than once\n'.format(rid, i+1))
 
     if not args.dry_run:
         for filename, data in csv_dataframe.items():

src/pyamsd/commands/upload_media.py

@@ -15,6 +15,9 @@ def run(args):
                        'moviefile': ['mp4']}
 
     with args.api.get_catalog() as cat:
+
+        name_uid_map = {obj.metadata['name']: obj for obj in cat}
+
         for ifn in sorted(args.upload_path.iterdir()):
             print(ifn.name)
 
@@ -28,6 +31,12 @@ def run(args):
                 print('No supported media format - skipping {0}'.format(fmt))
                 continue
 
+            if str(ifn.stem) in name_uid_map:
+                cat_obj = name_uid_map[str(ifn.stem)]
+                cat_obj_id = name_uid_map[str(ifn.stem)].id
+                print('{}: object {} exists - will be deleted'.format(ifn.name, cat_obj_id))
+                cat.delete(cat_obj_id)
+
             md = {
                 'collection': 'amsd',
                 'name': str(ifn.stem),

src/pyamsd/util.py

@@ -15,6 +15,7 @@
     [0, 'Place Created', 'place_created', ''],
     [1, 'Item type', 'item_type', ''],
     [1, 'Subtype', 'item_subtype', ''],
+    [0, 'State or territory', 'state_territory', ''],
     [1, 'Cultural region', 'cultural_region', ''],
     [1, 'Linguistic area', 'ling_area_1',
      r'Chirila\s*:\s*(.*?)  +Austlang\s*:\s*(.*?)\s*:(.*?)  +Glottolog\s*:\s*(.*)\s*'],
@@ -49,7 +50,7 @@
     [0, 'URL (source document)', 'url_source_1', ''],
     [0, 'URL (source document 2)', 'url_source_2', ''],
     [0, 'IRN', 'irn', r' *; *'],
-    [0, 'Related entries', 'related_entries', r' +'],
+    [0, 'Related entries', 'related_entries', r'[ ,;]+'],
     [0, 'Notes', 'notes', ''],
     [1, 'Data entry (OCCAMS)', 'data_entry', r'  +'],
     [1, 'Linked Filename', 'linked_filenames', r' *; *']