feat: custom dataset split sign (#4221)

* feat: custom dataset split sign

* feat: custom dataset split sign

packages/web/i18n/zh-CN/dataset.json

@@ -25,6 +25,7 @@
   "core.dataset.import.Adjust parameters": "调整参数",
   "custom_data_process_params": "自定义",
   "custom_data_process_params_desc": "自定义设置数据处理规则",
+  "custom_split_sign_tip": "允许你根据自定义的分隔符进行分块。通常用于已处理好的数据，使用特定的分隔符来精确分块。可以使用 | 符号表示多个分割符，例如：“。|.” 表示中英文句号。\n尽量避免使用正则相关特殊符号，例如: * () [] {} 等。",
   "data.ideal_chunk_length": "理想分块长度",
   "data_amount": "{{dataAmount}} 组数据, {{indexAmount}} 组索引",
   "data_index_num": "索引 {{index}}",
@@ -86,6 +87,14 @@
   "retain_collection": "调整训练参数",
   "retrain_task_submitted": "重新训练任务已提交",
   "same_api_collection": "存在相同的 API 集合",
+  "split_sign_break": "1 个换行符",
+  "split_sign_break2": "2 个换行符",
+  "split_sign_custom": "自定义",
+  "split_sign_exclamatiob": "感叹号",
+  "split_sign_null": "不设置",
+  "split_sign_period": "句号",
+  "split_sign_question": "问号",
+  "split_sign_semicolon": "分号",
   "start_sync_website_tip": "确认开始同步数据？将会删除旧数据后重新获取，请确认！",
   "sync_collection_failed": "同步集合错误，请检查是否能正常访问源文件",
   "sync_schedule": "定时同步",