Fix wrong offset_data being used for sparse files with an additional size PAX keyword

Author: mxmlnkn

Lib/tarfile.py

@@ -1541,6 +1541,12 @@ def _proc_pax(self, tarfile):
         except HeaderError as e:
             raise SubsequentHeaderError(str(e)) from None
 
+        # offset_data needs to be stored in case "size" is in pax_headers and
+        # the next TAR offset needs to be recomputed. next.offset_data may get
+        # overwritten when parsing sparse files and therefore cannot be used
+        # directly for the recomputation.
+        next_offset_data = next.offset_data
+
         # Process GNU sparse information.
         if "GNU.sparse.map" in pax_headers:
             # GNU extended sparse format version 0.1.
@@ -1563,9 +1569,10 @@ def _proc_pax(self, tarfile):
                 # If the extended header replaces the size field,
                 # we need to recalculate the offset where the next
                 # header starts.
-                offset = next.offset_data
+                offset = next_offset_data
                 if next.isreg() or next.type not in SUPPORTED_TYPES:
-                    offset += next._block(next.size)
+                    # Do not use use next.size here because it may contain the real size for sparse files.
+                    offset += next._block(int(pax_headers["size"]))
                 tarfile.offset = offset
 
         return next

Misc/NEWS.d/next/Library/2025-07-13-12-21-36.gh-issue-136602.9Q67Ns.rst

@@ -0,0 +1,2 @@
+Fix wrong `offset_data` being used for sparse files with an additional
+`size` PAX keyword.