improved

file_gen_util.py

@@ -12,17 +12,18 @@ def check_if_duplicates(list_of_elems):
     if len(dupe) > 0:
         print('THE FOLLOWING FILES ARE ATTACHED TO MORE THAN ONE IMAGE!!')
         for d in dupe:
-            print('  * ' + str(d))  # stringify just in case
+            print(str(d))  # stringify just in case
 
 
 def check_if_not_found(list_of_elems):
     if len(list_of_elems) > 0:
         print('DID NOT FIND!!')
         for i in list_of_elems:
-            print('  * ' + str(i))  # ditto.
+            print(str(i))  # stringify.
+        print('DID NOT FIND.')
 
 
-def find_row(replace_str, search, image_list, manifest_type, f):
+def find_row(replace_str, search, image_list, manifest_type, f, collection=""):
     found1 = 0
     search_term = ""
     if replace_str:
@@ -45,19 +46,20 @@ def find_row(replace_str, search, image_list, manifest_type, f):
                 found1 = 1
                 # Write to file
                 if manifest_type == 'map':
-                    f.write(row[1] + "," + row[2] + "," + row[3] + "," + search.strip() + "\n")
+                    f.write(collection + "," + row[1] + "," + row[2] + "," + row[3] + "," + search.strip() + "\n")
                     to_be_uploaded.append(search_term.strip())
                 else:
                     if manifest_type == 'segmentation':
                         f.write(search_term.strip() + "," + row[1] + "," + row[2] + "," + row[3].strip())
                         to_be_uploaded.append(row[3].strip())
                 break
-    return found1, key1
+    return found1, search.rstrip()
 
 
 def main(my_args):
     image_list = my_args['download']
     manifest_type = my_args['type']
+    collection_name = my_args['collection']
     replace_str = ''
     if my_args['string']:
         replace_str = my_args['string']
@@ -86,7 +88,7 @@ def main(my_args):
             f.write('segmentdir,studyid,clinicaltrialsubjectid,imageid\n')
 
         if manifest_type == 'map':
-            f.write('studyid,clinicaltrialsubjectid,imageid,filename\n')
+            f.write('collectionname,studyid,clinicaltrialsubjectid,imageid,filename\n')
 
         not_found = []
         if my_args['file']:
@@ -96,7 +98,7 @@ def main(my_args):
                     key = search_term
                     # skip blank lines
                     if len(search_term.strip()) > 0:
-                        found, key = find_row(replace_str, search_term, image_list, manifest_type, f)
+                        found, key = find_row(replace_str, search_term, image_list, manifest_type, f, collection_name)
                     if not found:
                         not_found.append(key)
         else:
@@ -125,10 +127,17 @@ def main(my_args):
     group.add_argument("-f", "--file", help="Path to input file", type=str)
     group.add_argument("-d", "--directory", help="Path to input directory", type=str)
     parser.add_argument("-dl", "--download", help="Path to downloaded quip file", required=True, type=str)
+    parser.add_argument("-c", "--collection", help="Collection name", required=False, type=str)
     parser.add_argument("-t", "--type", help="Type of manifest", required=True, type=str)
     parser.add_argument("-s", "--string", help="Substring to replace", required=False, type=str)
+
     args = vars(parser.parse_args())
 
+    if not args['collection'] and ("map" in args['type'].lower()):
+        parser.error("\n--type map requires --collection")
+
     # 1) Download httplinks.csv from PathDB
     # 2) ls -l | awk '{print $9}' > ~/myList.list
     main(args)
+    print('Done.')
+    exit(0)