From d7681302043c50c478f411a580c553e7d14d7467 Mon Sep 17 00:00:00 2001
From: Yongteng Lei <yongtengrey@outlook.com>
Date: Thu, 26 Jun 2025 17:46:53 +0800
Subject: [PATCH] Fix: chunk number error after re-parsing (#8513)

### What problem does this PR solve?

Fix chunk number error after re-parsing. #8503.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 api/apps/document_app.py            |  7 +++++++
 api/db/services/document_service.py | 18 ++++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/api/apps/document_app.py b/api/apps/document_app.py
index 68a76394f..90d62b0b3 100644
--- a/api/apps/document_app.py
+++ b/api/apps/document_app.py
@@ -365,6 +365,13 @@ def run():
                 info["progress_msg"] = ""
                 info["chunk_num"] = 0
                 info["token_num"] = 0
+
+            e, doc = DocumentService.get_by_id(id)
+            if not e:
+                return get_data_error_result(message="Document not found!")
+            if doc.run == TaskStatus.DONE.value:
+                DocumentService.clear_chunk_num_when_rerun(doc.id)
+
             DocumentService.update_by_id(id, info)
             tenant_id = DocumentService.get_tenant_id(id)
             if not tenant_id:
diff --git a/api/db/services/document_service.py b/api/db/services/document_service.py
index 8b7bc6660..c69f75aca 100644
--- a/api/db/services/document_service.py
+++ b/api/db/services/document_service.py
@@ -279,6 +279,24 @@ class DocumentService(CommonService):
             Knowledgebase.id == doc.kb_id).execute()
         return num
 
+
+    @classmethod
+    @DB.connection_context()
+    def clear_chunk_num_when_rerun(cls, doc_id):
+        doc = cls.model.get_by_id(doc_id)
+        assert doc, "Can't fine document in database."
+
+        num = (
+            Knowledgebase.update(
+                token_num=Knowledgebase.token_num - doc.token_num,
+                chunk_num=Knowledgebase.chunk_num - doc.chunk_num,
+            )
+            .where(Knowledgebase.id == doc.kb_id)
+            .execute()
+        )
+        return num
+
+
     @classmethod
     @DB.connection_context()
     def get_tenant_id(cls, doc_id):