feat: fix i18n missing keys and merge upstream/main (#24615)

Signed-off-by: -LAN- <laipz8200@outlook.com>
Signed-off-by: kenwoodjw <blackxin55+@gmail.com>
Signed-off-by: Yongtao Huang <yongtaoh2022@gmail.com>
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: GuanMu <ballmanjq@gmail.com>
Co-authored-by: Davide Delbianco <davide.delbianco@outlook.com>
Co-authored-by: NeatGuyCoding <15627489+NeatGuyCoding@users.noreply.github.com>
Co-authored-by: kenwoodjw <blackxin55+@gmail.com>
Co-authored-by: Yongtao Huang <yongtaoh2022@gmail.com>
Co-authored-by: Yongtao Huang <99629139+hyongtao-db@users.noreply.github.com>
Co-authored-by: Qiang Lee <18018968632@163.com>
Co-authored-by: 李强04 <liqiang04@gaotu.cn>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Asuka Minato <i@asukaminato.eu.org>
Co-authored-by: Matri Qi <matrixdom@126.com>
Co-authored-by: huayaoyue6 <huayaoyue@163.com>
Co-authored-by: Bowen Liang <liangbowen@gf.com.cn>
Co-authored-by: znn <jubinkumarsoni@gmail.com>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: yihong <zouzou0208@gmail.com>
Co-authored-by: Muke Wang <shaodwaaron@gmail.com>
Co-authored-by: wangmuke <wangmuke@kingsware.cn>
Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com>
Co-authored-by: quicksand <quicksandzn@gmail.com>
Co-authored-by: 非法操作 <hjlarry@163.com>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: Eric Guo <eric.guocz@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: jiangbo721 <jiangbo721@163.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: hjlarry <25834719+hjlarry@users.noreply.github.com>
Co-authored-by: lxsummer <35754229+lxjustdoit@users.noreply.github.com>
Co-authored-by: 湛露先生 <zhanluxianshen@163.com>
Co-authored-by: Guangdong Liu <liugddx@gmail.com>
Co-authored-by: QuantumGhost <obelisk.reg+git@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Yessenia-d <yessenia.contact@gmail.com>
Co-authored-by: huangzhuo1949 <167434202+huangzhuo1949@users.noreply.github.com>
Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com>
Co-authored-by: 17hz <0x149527@gmail.com>
Co-authored-by: Amy <1530140574@qq.com>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: Nite Knite <nkCoding@gmail.com>
Co-authored-by: Yeuoly <45712896+Yeuoly@users.noreply.github.com>
Co-authored-by: Petrus Han <petrus.hanks@gmail.com>
Co-authored-by: iamjoel <2120155+iamjoel@users.noreply.github.com>
Co-authored-by: Kalo Chin <frog.beepers.0n@icloud.com>
Co-authored-by: Ujjwal Maurya <ujjwalsbx@gmail.com>
Co-authored-by: Maries <xh001x@hotmail.com>

api/controllers/console/datasets/datasets_document.py

@@ -4,7 +4,7 @@ from typing import Literal, cast
 
 from flask import request
 from flask_login import current_user
-from flask_restful import Resource, marshal, marshal_with, reqparse
+from flask_restx import Resource, marshal, marshal_with, reqparse
 from sqlalchemy import asc, desc, select
 from werkzeug.exceptions import Forbidden, NotFound
 
@@ -54,6 +54,8 @@ from models import Dataset, DatasetProcessRule, Document, DocumentSegment, Uploa
 from services.dataset_service import DatasetService, DocumentService
 from services.entities.knowledge_entities.knowledge_entities import KnowledgeConfig
 
+logger = logging.getLogger(__name__)
+
 
 class DocumentResource(Resource):
     def get_document(self, dataset_id: str, document_id: str) -> Document:
@@ -468,25 +470,11 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
             return {"tokens": 0, "total_price": 0, "currency": "USD", "total_segments": 0, "preview": []}, 200
         data_process_rule = documents[0].dataset_process_rule
         data_process_rule_dict = data_process_rule.to_dict()
-        info_list = []
         extract_settings = []
         for document in documents:
             if document.indexing_status in {"completed", "error"}:
                 raise DocumentAlreadyFinishedError()
             data_source_info = document.data_source_info_dict
-            # format document files info
-            if data_source_info and "upload_file_id" in data_source_info:
-                file_id = data_source_info["upload_file_id"]
-                info_list.append(file_id)
-            # format document notion info
-            elif (
-                data_source_info and "notion_workspace_id" in data_source_info and "notion_page_id" in data_source_info
-            ):
-                pages = []
-                page = {"page_id": data_source_info["notion_page_id"], "type": data_source_info["type"]}
-                pages.append(page)
-                notion_info = {"workspace_id": data_source_info["notion_workspace_id"], "pages": pages}
-                info_list.append(notion_info)
 
             if document.data_source_type == "upload_file":
                 file_id = data_source_info["upload_file_id"]
@@ -966,7 +954,7 @@ class DocumentRetryApi(DocumentResource):
                     raise DocumentAlreadyFinishedError()
                 retry_documents.append(document)
             except Exception:
-                logging.exception("Failed to retry document, document id: %s", document_id)
+                logger.exception("Failed to retry document, document id: %s", document_id)
                 continue
         # retry document
         DocumentService.retry_document(dataset_id, retry_documents)