aboutsummaryrefslogtreecommitdiff
path: root/gnu/system/file-systems.scm
diff options
context:
space:
mode:
authorMaxim Cournoyer <maxim.cournoyer@gmail.com>2021-06-17 01:22:35 -0400
committerMaxim Cournoyer <maxim.cournoyer@gmail.com>2021-06-29 14:53:21 -0400
commit4f3bdc8f21657dbda857027b3ec8754dd4c7c67b (patch)
treec2a13dca9fdd301c8042696ea5f8f62dcfe43818 /gnu/system/file-systems.scm
parent6b0e55cde901dd5f6eae72cee10723b7739cadf7 (diff)
downloadguix-4f3bdc8f21657dbda857027b3ec8754dd4c7c67b.tar
guix-4f3bdc8f21657dbda857027b3ec8754dd4c7c67b.tar.gz
pack: Prevent duplicate files in tar archives.
Tar translate duplicate files in the archive into hard links. These can cause problems, as not every tool support them; for example dpkg doesn't. * gnu/system/file-systems.scm (reduce-directories): New procedure. (file-prefix?): Lift the restriction on file prefix. The procedure can be useful for comparing relative file names. Adjust doc. (file-name-depth): New procedure, extracted from ... (btrfs-store-subvolume-file-name): ... here. * guix/scripts/pack.scm (self-contained-tarball/builder): Use reduce-directories. * tests/file-systems.scm ("reduce-directories"): New test.
Diffstat (limited to 'gnu/system/file-systems.scm')
-rw-r--r--gnu/system/file-systems.scm56
1 files changed, 38 insertions, 18 deletions
diff --git a/gnu/system/file-systems.scm b/gnu/system/file-systems.scm
index 464e87cb18..fb87bfc85b 100644
--- a/gnu/system/file-systems.scm
+++ b/gnu/system/file-systems.scm
@@ -55,6 +55,7 @@
file-system-dependencies
file-system-location
+ reduce-directories
file-system-type-predicate
btrfs-subvolume?
btrfs-store-subvolume-file-name
@@ -231,8 +232,8 @@
(char-set-complement (char-set #\/)))
(define (file-prefix? file1 file2)
- "Return #t if FILE1 denotes the name of a file that is a parent of FILE2,
-where both FILE1 and FILE2 are absolute file name. For example:
+ "Return #t if FILE1 denotes the name of a file that is a parent of FILE2.
+For example:
(file-prefix? \"/gnu\" \"/gnu/store\")
=> #t
@@ -240,19 +241,41 @@ where both FILE1 and FILE2 are absolute file name. For example:
(file-prefix? \"/gn\" \"/gnu/store\")
=> #f
"
- (and (string-prefix? "/" file1)
- (string-prefix? "/" file2)
- (let loop ((file1 (string-tokenize file1 %not-slash))
- (file2 (string-tokenize file2 %not-slash)))
- (match file1
- (()
- #t)
- ((head1 tail1 ...)
- (match file2
- ((head2 tail2 ...)
- (and (string=? head1 head2) (loop tail1 tail2)))
- (()
- #f)))))))
+ (let loop ((file1 (string-tokenize file1 %not-slash))
+ (file2 (string-tokenize file2 %not-slash)))
+ (match file1
+ (()
+ #t)
+ ((head1 tail1 ...)
+ (match file2
+ ((head2 tail2 ...)
+ (and (string=? head1 head2) (loop tail1 tail2)))
+ (()
+ #f))))))
+
+(define (file-name-depth file-name)
+ (length (string-tokenize file-name %not-slash)))
+
+(define (reduce-directories file-names)
+ "Eliminate entries in FILE-NAMES that are children of other entries in
+FILE-NAMES. This is for example useful when passing a list of files to GNU
+tar, which would otherwise descend into each directory passed and archive the
+duplicate files as hard links, which can be undesirable."
+ (let* ((file-names/sorted
+ ;; Ascending sort by file hierarchy depth, then by file name length.
+ (stable-sort (delete-duplicates file-names)
+ (lambda (f1 f2)
+ (let ((depth1 (file-name-depth f1))
+ (depth2 (file-name-depth f2)))
+ (if (= depth1 depth2)
+ (string< f1 f2)
+ (< depth1 depth2)))))))
+ (reverse (fold (lambda (file-name results)
+ (if (find (cut file-prefix? <> file-name) results)
+ results ;parent found -- skipping
+ (cons file-name results)))
+ '()
+ file-names/sorted))))
(define* (file-system-device->string device #:key uuid-type)
"Return the string representations of the DEVICE field of a <file-system>
@@ -624,9 +647,6 @@ store is located, else #f."
s
(string-append "/" s)))
- (define (file-name-depth file-name)
- (length (string-tokenize file-name %not-slash)))
-
(and-let* ((btrfs-subvolume-fs (filter btrfs-subvolume? file-systems))
(btrfs-subvolume-fs*
(sort btrfs-subvolume-fs