apply same fix as asmyma : track title instead of track audio file name, and promote main versions

app.py

@@ -38,6 +38,42 @@ encoder_text = tf.keras.models.load_model(
     "encoder_text_retrievaltext_bmg_221022_54_clean"
 )
 
+fixation_id_to_file_name = {}
+for file_name, infos in dict_catalog.items():
+    # we want only main versions
+    if infos["Parent fixation id"].strip():
+        continue
+    fixation_id_to_file_name[infos["Fixation id"].strip()] = file_name
+
+child_to_parent_filename = {}
+count = count_failed = 0
+for file_name, infos in dict_catalog.items():
+    if not infos["Parent fixation id"].strip():
+        continue
+
+    count += 1
+    try:
+        child_to_parent_filename[file_name] = fixation_id_to_file_name[
+            infos["Parent fixation id"].strip()
+        ]
+    except Exception as e:
+        print(f"No parent for {file_name} : {e}")
+        count_failed += 1
+
+print(f"{count_failed} tracks have no parent / {count} tracks")
+
+parent_file_names = set(list(fixation_id_to_file_name.values()))
+
+file_name_to_url = {}
+for file_url in url_dict.values():
+    file_name = os.path.splitext(os.path.basename(file_url))[0]
+    if file_name not in parent_file_names:
+        continue
+    file_name_to_url[file_name] = file_url
+
+parent_file_names = []
+fixation_id_to_file_name = []
+
 
 def process(prompt, lang):
     now = datetime.datetime.now()
@@ -68,15 +104,35 @@ def process(prompt, lang):
     with open(output_csv, "w") as w:
         writer = csv.writer(w)
         header = False
+        already = set()
         for position, top in enumerate(I[0]):
             if len(formated) / 2 >= max_output:
                 break
 
             file = os.path.splitext(os.path.basename(audio_names[top]))[0]
+            top = get_url_myma(top, audio_names, url_dict)
+            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:
                     writer.writerow(list(dict_catalog[file].keys()))
                     header = True
+                file_name = dict_catalog[file]["Track name"]
+                try:
+                    file_name += " - " + dict_catalog[file]["Composer1 full name"]
+                except:
+                    pass
+                try:
+                    file_name += " - " + dict_catalog[file]["Album name"]
+                except:
+                    pass
                 writer.writerow(dict_catalog[file].values())
             else:
                 writer.writerow([file, "no metadata provided"])
@@ -84,8 +140,8 @@ def process(prompt, lang):
             try:
                 formated.append(
                     {
-                        "f": f"{position+1} - {file}",
-                        "t": get_url_myma(top, audio_names, url_dict),
+                        "f": f"{position+1} - {file_name}",
+                        "t": top,
                     }
                 )
             except: