From 90758724357856accc2e9e39ce2d79195c06a6ee Mon Sep 17 00:00:00 2001
From: Idriss Sbaaoui <112825897+6ba3i@users.noreply.github.com>
Date: Thu, 30 Apr 2026 11:55:02 +0800
Subject: [PATCH] Fix: Manual/Naive outline tuple unpack crash (#14518)

### What problem does this PR solve?

This fixes a crash in Manual and Naive parsing when PDF outlines include
page numbers as a third tuple value. It makes outline unpacking accept
extra values so parsing no longer fails. fixes #14411

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 rag/app/manual.py | 2 +-
 rag/app/naive.py  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/rag/app/manual.py b/rag/app/manual.py
index b9afdbf725..b3f5f2edc1 100644
--- a/rag/app/manual.py
+++ b/rag/app/manual.py
@@ -270,7 +270,7 @@ def chunk(filename, binary=None, from_page=0, to_page=MAXIMUM_PAGE_NUMBER, lang=
         if res and pdf_parser and getattr(pdf_parser, "outlines", None):
             res[0]["__outline__"] = [
                 {"title": title, "depth": depth}
-                for title, depth in pdf_parser.outlines
+                for title, depth, *_ in pdf_parser.outlines
             ]
         return res
 
diff --git a/rag/app/naive.py b/rag/app/naive.py
index 513f503b65..90d1b42858 100644
--- a/rag/app/naive.py
+++ b/rag/app/naive.py
@@ -1133,7 +1133,7 @@ def chunk(filename, binary=None, from_page=0, to_page=MAXIMUM_PAGE_NUMBER, lang=
     if res and pdf_parser and getattr(pdf_parser, "outlines", None):
         res[0]["__outline__"] = [
             {"title": title, "depth": depth}
-            for title, depth in pdf_parser.outlines
+            for title, depth, *_ in pdf_parser.outlines
         ]
 
     return res