GNU bug report logs - #61722
(guix cpio) produces corrupted archives when there are non-ASCII filenames

Previous Next

Full log

Message #8 received at 61722 <at> debbugs.gnu.org (full text, mbox):

From: Maxim Cournoyer <maxim.cournoyer <at> gmail.com>
To: 61722 <at> debbugs.gnu.org
Cc: Josselin Poiret <dev <at> jpoiret.xyz>, Tobias Geerinckx-Rice <me <at> tobias.gr>,
 Maxim Cournoyer <maxim.cournoyer <at> gmail.com>,
 Simon Tournier <zimon.toutoune <at> gmail.com>, Mathieu Othacehe <othacehe <at> gnu.org>,
 Ludovic Courtès <ludo <at> gnu.org>,
 Christopher Baines <mail <at> cbaines.net>, Ricardo Wurmus <rekado <at> elephly.net>
Subject: [PATCH] cpio: Properly handle Unicode characters in file names.
Date: Thu, 23 Feb 2023 23:54:01 -0500

Fixes <https://issues.guix.gnu.org/61722>.

* guix/cpio.scm (file->cpio-header): Compute the file name length in bytes rather than in
characters.
(file->cpio-header*, special-file->cpio-header*): Likewise.
(write-cpio-archive): Likewise, and write the file name as UTF-8 bytes, not
textually, to avoid encoding it as ISO-8859-1.

---

 guix/cpio.scm | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/guix/cpio.scm b/guix/cpio.scm
index d4a7d5f1e0..8fd7552450 100644
--- a/guix/cpio.scm
+++ b/guix/cpio.scm
@@ -170,7 +170,8 @@ (define* (file->cpio-header file #:optional (file-name file)
                       #:size (stat:size st)
                       #:dev (stat:dev st)
                       #:rdev (stat:rdev st)
-                      #:name-size (string-length file-name))))
+                      #:name-size (bytevector-length
+                                   (string->utf8 file-name)))))
 
 (define* (file->cpio-header* file
                              #:optional (file-name file)
@@ -182,7 +183,8 @@ (define* (file->cpio-header* file
     (make-cpio-header #:mode (stat:mode st)
                       #:nlink (stat:nlink st)
                       #:size (stat:size st)
-                      #:name-size (string-length file-name))))
+                      #:name-size (bytevector-length
+                                   (string->utf8 file-name)))))
 
 (define* (special-file->cpio-header* file
                                      device-type
@@ -201,7 +203,8 @@ (define* (special-file->cpio-header* file
                                     permission-bits)
                     #:nlink 1
                     #:rdev (device-number device-major device-minor)
-                    #:name-size (string-length file-name)))
+                    #:name-size (bytevector-length
+                                 (string->utf8 file-name))))
 
 (define %trailer
   "TRAILER!!!")
@@ -237,7 +240,7 @@ (define (dump-file file)
 
       ;; We're padding the header + following file name + trailing zero, and
       ;; the header is 110 byte long.
-      (write-padding (+ 110 1 (string-length file)) port)
+      (write-padding (+ 110 (bytevector-length (string->utf8 file)) 1) port)
 
       (case (mode->type (cpio-header-mode header))
         ((regular)
@@ -246,7 +249,7 @@ (define (dump-file file)
              (dump-port input port))))
         ((symlink)
          (let ((target (readlink file)))
-           (put-string port target)))
+           (put-bytevector port (string->utf8 target))))
         ((directory)
          #t)
         ((block-special)

base-commit: c756c62cfdba8d4079be1ba9e370779b850f16b6
-- 
2.39.1

Previous Next

GNU bug tracking system
Copyright (C) 1999 Darren O. Benham, 1997,2003 nCipher Corporation Ltd, 1994-97 Ian Jackson.