Add reminder about old categories

2023-12-02 00:17:58 +02:00 · 2023-12-02 00:17:58 +02:00 · 5dd850d1cb
parent 46f533746e
commit 5dd850d1cb
1 changed files with 2 additions and 0 deletions
--- a/africat/aa_create_dataset.py
+++ b/africat/aa_create_dataset.py
@ -96,6 +96,8 @@ def parse_and_extract(input_dir, verbose):

          cats = list()
          for cat in doc.findall('./category'):
+            # TODO check against a list of current categories,
+            # and strip any non-current categories
            cats.append(cat.text)
          #entry["categories"] = cats          # if you want a list
          entry["categories"] = ";".join(cats) # if you want a string