From 92c81b1833a42d745278f5c0bbd78446e96ed9d9 Mon Sep 17 00:00:00 2001
From: zlyszx <74173496+zlyszx@users.noreply.github.com>
Date: Thu, 23 Oct 2025 12:32:34 +0800
Subject: [PATCH] fix: document word_count appear negative (#27313)

Co-authored-by: zlyszx <zlyszx>
---
 api/core/indexing_runner.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/api/core/indexing_runner.py b/api/core/indexing_runner.py
index c430fba0b9..36b38b7b45 100644
--- a/api/core/indexing_runner.py
+++ b/api/core/indexing_runner.py
@@ -415,7 +415,6 @@ class IndexingRunner:
             document_id=dataset_document.id,
             after_indexing_status="splitting",
             extra_update_params={
-                DatasetDocument.word_count: sum(len(text_doc.page_content) for text_doc in text_docs),
                 DatasetDocument.parsing_completed_at: naive_utc_now(),
             },
         )
@@ -755,6 +754,7 @@ class IndexingRunner:
             extra_update_params={
                 DatasetDocument.cleaning_completed_at: cur_time,
                 DatasetDocument.splitting_completed_at: cur_time,
+                DatasetDocument.word_count: sum(len(doc.page_content) for doc in documents),
             },
         )