try to promote main versions

app.py

@@ -30,7 +30,7 @@ python_path = hf_hub_download(
 sys.path.append(os.environ["PRIVATE_DIR"])
 from models import *
 
-max_results = 100
+max_results = 200
 max_output = 50
 
 # global (faster)
@@ -40,6 +40,31 @@ catalog = get_catalog()
 url_dict = get_durl_myma()
 dict_catalog = get_dict_catalog()
 
+fixation_id_to_file_name = {}
+for file_name, infos in dict_catalog.items():
+    # we want only main versions
+    if not infos["Parent fixation id"]:
+        continue
+    fixation_id_to_file_name[infos["Fixation id"]] = file_name
+
+child_to_parent_filename = {}
+for file_name, infos in dict_catalog.items():
+    if infos["Parent fixation id"]:
+        child_to_parent_filename[file_name] = fixation_id_to_file_name[
+            infos["Parent fixation id"]
+        ]
+
+parent_file_names = set(list(fixation_id_to_file_name.values()))
+fixation_id_to_file_name = {}
+
+file_name_to_url = {}
+for file_name, file_url in zip(ind_filenames, url_dict):
+    if file_name not in parent_file_names:
+        continue
+    file_name_to_url[file_name] = file_url
+
+parent_file_names = []
+
 
 def download_audio(id_video):
     id = id_video.split("?v=")[-1][:11]
@@ -85,11 +110,20 @@ def process(file_name, embed_html_all):
     with open(output_csv, "w") as w:
         writer = csv.writer(w)
         header = False
+        already = set()
         for position, top in enumerate(tops):
             if len(formated) / 2 >= max_output:
                 break
 
             file = os.path.splitext(os.path.basename(top))[0]
+            try:
+                file = child_to_parent_filename[file]
+                top = file_name_to_url[file]
+            except KeyError:
+                pass
+            if file in already:
+                continue
+            already.add(file)
             file_name = file
             if file in dict_catalog:
                 if not header: