Miscs (Interro 28)

annotating_by_label.py

@@ -160,11 +160,35 @@ def main():
 
         used_prefixes.add(unique_prefix)
 
+        existing_items = set()
+        max_existing_group = 0
+
+
+        if not args.overwrite and os.path.exists(bgnot_dir):
+            for d in os.listdir(bgnot_dir):
+                if d.startswith(f"{unique_prefix} G"):
+                    try:
+                        g_id = int(d.split(' G')[-1])
+                        max_existing_group = max(max_existing_group, g_id)
+                    except ValueError:
+                        pass
+
+                    bnote_path = os.path.join(bgnot_dir, d, "bnote.json")
+                    if os.path.exists(bnote_path):
+                        with open(bnote_path, "r") as bf:
+                            bdata = json.load(bf)
+                            for img in bdata.get("images", []):
+                                existing_items.add((img["id"], img["label"]))
+
         items_to_render = []
         for sid, lbls in results.items():
             for lbl in labels:
                 if lbl in lbls:
-                    items_to_render.append((sid, lbl, lbls[lbl]))
+                    # Only add if it hasn't been generated yet
+                    if (sid, lbl) not in existing_items:
+                        items_to_render.append((sid, lbl, lbls[lbl]))
+        if not items_to_render:
+            continue
 
         # Sort structurally: by student id and label
         items_to_render.sort(key=lambda x: (natural_key(x[0]), natural_key(x[1])))
@@ -217,7 +241,7 @@ def main():
             batches = batches2
 
         for i, batch in enumerate(batches, 1):
-            save_batch(batch, unique_prefix, i, root_dir, args.overwrite)
+            save_batch(batch, unique_prefix, max_existing_group + i, root_dir, args.overwrite)
 
 if __name__ == "__main__":
     main()