From 70e4ccb00e1f0547406f531bed288b98563b2d7e Mon Sep 17 00:00:00 2001
From: Ekalabya Ghosh <ekalabya2010@gmail.com>
Date: Fri, 25 Sep 2026 23:13:12 +0530
Subject: [PATCH] gh-158181: fix IndexError instead of ReadError on truncated
 GNU sparse header

_proc_sparse() read the extended header block for a GNU sparse member
with a plain read(BLOCKSIZE) instead of checking for a short/empty
result, so a truncated archive whose sparse member has isextended set
made nti() raise IndexError (s[0] on an empty buffer) instead of the
documented ReadError. Raise ReadError directly when the read is
short, matching the pattern used elsewhere in this module for
truncated data.
---
 Lib/tarfile.py                                                 | 2 ++
 .../Library/2026-09-25-17-42-56.gh-issue-158181.v7PCZg.rst     | 3 +++
 2 files changed, 5 insertions(+)
 create mode 100644 Misc/NEWS.d/next/Library/2026-09-25-17-42-56.gh-issue-158181.v7PCZg.rst

diff --git a/Lib/tarfile.py b/Lib/tarfile.py
index a4f9ce3311f6dad..e995f9d5c867211 100644
--- a/Lib/tarfile.py
+++ b/Lib/tarfile.py
@@ -1494,6 +1494,8 @@ def _proc_sparse(self, tarfile):
         # Collect sparse structures from extended header blocks.
         while isextended:
             buf = tarfile.fileobj.read(BLOCKSIZE)
+            if len(buf) < BLOCKSIZE:
+                raise ReadError("unexpected end of data")
             pos = 0
             for i in range(21):
                 try:
diff --git a/Misc/NEWS.d/next/Library/2026-09-25-17-42-56.gh-issue-158181.v7PCZg.rst b/Misc/NEWS.d/next/Library/2026-09-25-17-42-56.gh-issue-158181.v7PCZg.rst
new file mode 100644
index 000000000000000..20d5424cf36a885
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2026-09-25-17-42-56.gh-issue-158181.v7PCZg.rst
@@ -0,0 +1,3 @@
+Fix :exc:`IndexError` instead of :exc:`tarfile.ReadError` when
+:mod:`tarfile` reads a truncated GNU sparse member whose extended header
+block is missing or short.