Update processor.py

processor.py

@@ -12,51 +12,71 @@ class DatasetCommandCenter:
         self.token = token
 
     def get_dataset_metadata(self, dataset_id):
+        configs = []
+        splits = []
+        license_name = "unknown"
+
+        # 1. Get Configs
         try:
-            try:
-                configs = get_dataset_config_names(dataset_id, token=self.token)
-            except:
-                configs = ['default']
-            try:
-                infos = get_dataset_infos(dataset_id, token=self.token)
-                first_conf = configs[0]
-                if first_conf in infos:
-                    splits = list(infos[first_conf].splits.keys())
-                else:
-                    splits = list(infos.values())[0].splits.keys()
-            except:
-                splits = ['train', 'test', 'validation']
-            # license    
-            try:
-                configs = get_dataset_config_names(dataset_id, token=self.token)
-            except:
-                configs = ['default']
+            configs = get_dataset_config_names(dataset_id, token=self.token)
+        except Exception as e:
+            logger.warning(f"Could not fetch configs for {dataset_id}: {e}")
+            # Fallback: if we can't get configs, assume 'default'
+            configs = ['default']
+
+        # 2. Get Splits & License
+        # Many datasets return 404 on dataset_infos.json. We must catch this.
+        try:
+            selected_config = configs[0] if configs else 'default'
             
-            license_name = "unknown"
-            try:
-                infos = get_dataset_infos(dataset_id, token=self.token)
-                # Try to grab license from first config
-                first = list(infos.values())[0]
-                license_name = first.license or "unknown"
-            except:
-                pass
-    
-            return {
-                "status": "success", 
-                "configs": configs, 
-                # We assume user will pick splits later, just return configs + license hint
-                "license_detected": license_name
-            }
+            # This API call frequently fails on datasets without metadata cards
+            infos = get_dataset_infos(dataset_id, token=self.token)
+            
+            # Attempt to find the info object for our config
+            info_obj = None
+            if selected_config in infos:
+                info_obj = infos[selected_config]
+            elif 'default' in infos:
+                info_obj = infos['default']
+            elif len(infos) > 0:
+                # Fallback to the first available if names don't match
+                info_obj = list(infos.values())[0]
+
+            if info_obj:
+                splits = list(info_obj.splits.keys())
+                license_name = info_obj.license or "unknown"
+                
         except Exception as e:
-            return {"status": "error", "message": str(e)}
+            logger.warning(f"Could not fetch dataset_infos (using fallbacks): {e}")
+            # Safe Fallback if metadata fails
+            splits = ['train', 'test', 'validation']
+            license_name = "unknown"
+
+        # Ensure we NEVER return None for lists
+        return {
+            "status": "success", 
+            "configs": configs if configs else ['default'], 
+            "splits": splits if splits else ['train'],
+            "license_detected": license_name
+        }
 
     def get_splits_for_config(self, dataset_id, config_name):
+        splits = []
         try:
             infos = get_dataset_infos(dataset_id, config_name=config_name, token=self.token)
-            splits = list(infos[config_name].splits.keys())
-            return {"status": "success", "splits": splits}
-        except:
-            return {"status": "success", "splits": ['train', 'test', 'validation']}
+            
+            if config_name in infos:
+                splits = list(infos[config_name].splits.keys())
+            elif len(infos) > 0:
+                # Fallback to first available
+                splits = list(infos.values())[0].splits.keys()
+                
+        except Exception as e:
+            logger.warning(f"Could not fetch splits for config {config_name}: {e}")
+            # Fallback
+            splits = ['train', 'test', 'validation']
+            
+        return {"status": "success", "splits": list(splits) if splits else ['train']}
 
     # --- HELPER: Recursive JSON/Dot Notation Getter ---
     def _get_value_by_path(self, obj, path):