From 33f72b19ec8c4b460c1685da5ecdb3c57d4c8d6f Mon Sep 17 00:00:00 2001
From: weijie <34210233+shiweijiezero@users.noreply.github.com>
Date: Thu, 18 Apr 2024 12:02:02 +0800
Subject: [PATCH] fix Bug: KeyError: 'text' Corresponding to issue #296 (#300)

* fix Bug: KeyError: 'text'

File data_juice/config/config.py lines 418-429 did not consider the situation when arg: text_key was initialized to 'text', resulting in arg: text_key not being updated properly and always being initialized to the value of 'text'

* Fix Bug: key_text do not update correctly

* Update config.py

Normalize Format
---
 data_juicer/config/config.py | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/data_juicer/config/config.py b/data_juicer/config/config.py
index 05fbad14c..5fbf3494f 100644
--- a/data_juicer/config/config.py
+++ b/data_juicer/config/config.py
@@ -268,8 +268,8 @@ def init_configs(args=None):
 
     try:
         cfg = parser.parse_args(args=args)
-        cfg = update_op_process(cfg, parser)
         cfg = init_setup_from_cfg(cfg)
+        cfg = update_op_process(cfg, parser)
 
         # copy the config file into the work directory
         config_backup(cfg)
@@ -422,11 +422,15 @@ def init_setup_from_cfg(cfg):
                     'audio_key': cfg.audio_key,
                     'video_key': cfg.video_key,
                 }
-            elif args['text_key'] is None:
-                args['text_key'] = text_key
-                args['image_key'] = cfg.image_key
-                args['audio_key'] = cfg.audio_key
-                args['video_key'] = cfg.video_key
+            else:
+                if 'text_key' not in args or args['text_key'] is None:
+                    args['text_key'] = text_key
+                if 'image_key' not in args or args['image_key'] is None:
+                    args['image_key'] = cfg.image_key
+                if 'audio_key' not in args or args['audio_key'] is None:
+                    args['audio_key'] = cfg.audio_key
+                if 'video_key' not in args or args['video_key'] is None:
+                    args['video_key'] = cfg.video_key
             op[op_name] = args
 
     return cfg