bug#59109: 29.0.50; package-tests failing since feature/package+vc merge

bug#59109: 29.0.50; package-tests failing since feature/package+vc merge

[Basil L. Contovounesios via Bug reports for GNU Emacs, the Swiss army knife of text editors]

[-- Attachment #1: Type: text/plain, Size: 837 bytes --]

Several tests in test/lisp/emacs-lisp/package-tests.el have been failing
on my end since the following commit:

  Merge branch 'feature/package+vc'
  5fa2f11679 2022-11-04 18:57:45 +0100
  https://git.sv.gnu.org/cgit/emacs.git/commit/?id=5fa2f11679

The failures do not happen on the merge commit's first parent:

  * lisp/simple.el (function-documentation): Fix bug#59014
  616aa23d8a 2022-11-04 11:59:51 -0400
  https://git.sv.gnu.org/cgit/emacs.git/commit/?id=616aa23d8a

I attach a log of building Emacs followed by two invocations of
'make test/package-tests', the first using the suite's .el file and the
second using the .elc.  The failures are the same either way.  Each run
is preceded by "echo '>>> TEST EL[C]'" for easier locating in the log.

Let me know if you'd like me to run anything else on my end.

Thanks,

-- 
Basil


[-- Attachment #2: package-tests.txt.gz --]
[-- Type: application/gzip, Size: 39916 bytes --]

[-- Attachment #3: Type: text/plain, Size: 2969 bytes --]


In GNU Emacs 29.0.50 (build 1, x86_64-pc-linux-gnu, GTK+ Version
 3.24.34, cairo version 1.16.0) of 2022-11-07 built on tia
Repository revision: 5fa2f116799b8a7c17ff6eedd6e1b1af077c116b
Repository branch: HEAD
Windowing system distributor 'The X.Org Foundation', version 11.0.12101004
System Description: Debian GNU/Linux bookworm/sid

Configured features:
ACL CAIRO DBUS FREETYPE GIF GLIB GMP GNUTLS GPM GSETTINGS HARFBUZZ JPEG
JSON LCMS2 LIBOTF LIBSELINUX LIBSYSTEMD LIBXML2 M17N_FLT MODULES NOTIFY
INOTIFY PDUMPER PNG RSVG SECCOMP SOUND SQLITE3 THREADS TIFF
TOOLKIT_SCROLL_BARS WEBP X11 XDBE XIM XINPUT2 XPM GTK3 ZLIB

Important settings:
  value of $LANG: en_IE.UTF-8
  value of $XMODIFIERS: @im=ibus
  locale-coding-system: utf-8-unix

Major mode: Lisp Interaction

Minor modes in effect:
  tooltip-mode: t
  global-eldoc-mode: t
  eldoc-mode: t
  show-paren-mode: t
  electric-indent-mode: t
  mouse-wheel-mode: t
  tool-bar-mode: t
  menu-bar-mode: t
  file-name-shadow-mode: t
  global-font-lock-mode: t
  font-lock-mode: t
  blink-cursor-mode: t
  line-number-mode: t
  indent-tabs-mode: t
  transient-mark-mode: t
  auto-composition-mode: t
  auto-encryption-mode: t
  auto-compression-mode: t

Load-path shadows:
None found.

Features:
(shadow sort mail-extr emacsbug message mailcap yank-media puny dired
dired-loaddefs rfc822 mml mml-sec password-cache epa derived epg rfc6068
epg-config gnus-util text-property-search time-date subr-x mm-decode
mm-bodies mm-encode mail-parse rfc2231 mailabbrev gmm-utils mailheader
cl-loaddefs cl-lib sendmail rfc2047 rfc2045 ietf-drums mm-util
mail-prsvr mail-utils rmc iso-transl tooltip cconv eldoc paren electric
uniquify ediff-hook vc-hooks lisp-float-type elisp-mode mwheel
term/x-win x-win term/common-win x-dnd tool-bar dnd fontset image
regexp-opt fringe tabulated-list replace newcomment text-mode lisp-mode
prog-mode register page tab-bar menu-bar rfn-eshadow isearch easymenu
timer select scroll-bar mouse jit-lock font-lock syntax font-core
term/tty-colors frame minibuffer nadvice seq simple cl-generic
indonesian philippine cham georgian utf-8-lang misc-lang vietnamese
tibetan thai tai-viet lao korean japanese eucjp-ms cp51932 hebrew greek
romanian slovak czech european ethiopic indian cyrillic chinese
composite emoji-zwj charscript charprop case-table epa-hook
jka-cmpr-hook help abbrev obarray oclosure cl-preloaded button loaddefs
theme-loaddefs faces cus-face macroexp files window text-properties
overlay sha1 md5 base64 format env code-pages mule custom widget keymap
hashtable-print-readable backquote threads dbusbind inotify lcms2
dynamic-setting system-font-setting font-render-setting cairo
move-toolbar gtk x-toolkit xinput2 x multi-tty make-network-process
emacs)

Memory information:
((conses 16 35905 6019)
 (symbols 48 5114 0)
 (strings 32 13075 1650)
 (string-bytes 1 370964)
 (vectors 16 9275)
 (vector-slots 8 147475 8338)
 (floats 8 21 23)
 (intervals 56 208 0)
 (buffers 984 10))

bug#59109: 29.0.50; package-tests failing since feature/package+vc merge

[Eli Zaretskii]

> Cc: Philip Kaludercic <philipk@posteo.net>
> Date: Mon, 07 Nov 2022 21:34:13 +0200
> From:  "Basil L. Contovounesios" via "Bug reports for GNU Emacs,
>  the Swiss army knife of text editors" <bug-gnu-emacs@gnu.org>
> 
> Several tests in test/lisp/emacs-lisp/package-tests.el have been failing
> on my end since the following commit:
> 
>   Merge branch 'feature/package+vc'
>   5fa2f11679 2022-11-04 18:57:45 +0100
>   https://git.sv.gnu.org/cgit/emacs.git/commit/?id=5fa2f11679
> 
> The failures do not happen on the merge commit's first parent:
> 
>   * lisp/simple.el (function-documentation): Fix bug#59014
>   616aa23d8a 2022-11-04 11:59:51 -0400
>   https://git.sv.gnu.org/cgit/emacs.git/commit/?id=616aa23d8a

I suggest to take a good look at the changes brought by the merge.
I've discovered today that this very merge caused us to lose the Local
variables section of etc/NEWS (didn't everybody notice Emacs is
suddenly visiting NEWS in Fundamental mode?).  This was certainly not
intended, so I wonder what other unintended changes we acquired
through that merge.  Maybe some of the failures you see have similar
causes.

bug#59109: 29.0.50; package-tests failing since feature/package+vc merge

[Basil L. Contovounesios via Bug reports for GNU Emacs, the Swiss army knife of text editors]

Eli Zaretskii [2022-11-07 14:43 -0500] wrote:

> I suggest to take a good look at the changes brought by the merge.

Sorry, I will almost certainly not be in a position to review the
changes carefully over the coming month.  I hope Philip or someone else
will find the time to address the issues.

Thanks,

-- 
Basil

bug#59109: 29.0.50; package-tests failing since feature/package+vc merge

[Philip Kaludercic]

"Basil L. Contovounesios" <contovob@tcd.ie> writes:

> Eli Zaretskii [2022-11-07 14:43 -0500] wrote:
>
>> I suggest to take a good look at the changes brought by the merge.
>
> Sorry, I will almost certainly not be in a position to review the
> changes carefully over the coming month.  I hope Philip or someone else
> will find the time to address the issues.

I am currently also a bit strained on time, but I'll try to take tackle
the issue over the next few evenings.

> Thanks,

bug#59109: 29.0.50; package-tests failing since feature/package+vc merge

[Philip Kaludercic]

"Basil L. Contovounesios" <contovob@tcd.ie> writes:

> Several tests in test/lisp/emacs-lisp/package-tests.el have been failing
> on my end since the following commit:
>
>   Merge branch 'feature/package+vc'
>   5fa2f11679 2022-11-04 18:57:45 +0100
>   https://git.sv.gnu.org/cgit/emacs.git/commit/?id=5fa2f11679
>
> The failures do not happen on the merge commit's first parent:
>
>   * lisp/simple.el (function-documentation): Fix bug#59014
>   616aa23d8a 2022-11-04 11:59:51 -0400
>   https://git.sv.gnu.org/cgit/emacs.git/commit/?id=616aa23d8a
>
> I attach a log of building Emacs followed by two invocations of
> 'make test/package-tests', the first using the suite's .el file and the
> second using the .elc.  The failures are the same either way.  Each run
> is preceded by "echo '>>> TEST EL[C]'" for easier locating in the log.
>
> Let me know if you'd like me to run anything else on my end.
>
> Thanks,

With the latest changes pushed to scratch/package-vc-fixes I have
reduced the number of failing tests to three:

--8<---------------cut here---------------start------------->8---
Selector: t
Passed:  33
Failed:  3 (3 unexpected)
Skipped: 1
Total:   37/37

Started at:   2022-11-11 19:19:53+0100
Finished.
Finished at:  2022-11-11 19:20:14+0100

..........F..............FF.....s....

F package-test-install-multifile
    Check properties of the installed multi-file package.
    (ert-test-failed
     ((should
       (file-exists-p
	(expand-file-name fn pkg-dir)))
      :form
      (file-exists-p "/tmp/emacs-test-4NLfrT-package/multi-file-0.2.3/multi-file-sub.elc")
      :value nil))

F package-test-macro-compilation
    "Activation has to be done before compilation, so that if we’re
    (ert-test-failed
 ((should
   (equal
    (macro-problem-func)
    '(1 b)))
  :form
  (equal
   (progn a b)
   (1 b))
  :value nil :explanation
  (proper-lists-of-different-length 3 2
				    (progn a b)
				    (1 b)
				    first-mismatch-at 0)))

F package-test-macro-compilation-gz
    Built-in’s can be superseded as well.
    (ert-test-failed
 ((should
   (member
    (expand-file-name "macro-builtin-aux.elc" dir)
    (mapcar #'car load-history)))
  :form
  (member "/home/philip/Source/emacs/test/lisp/emacs-lisp/package-resources/macro-builtin-package-1.0/macro-builtin-aux.elc"
	  ("/tmp/emacs-test-F81fle-package/macro-problem-2.0/macro-problem-autoloads.el" "/tmp/emacs-test-F81fle-package/macro-problem-1.0/macro-problem-autoloads.el" "/tmp/emacs-test-MaJv5k-package/simple-single-1.3/simple-single-autoloads.el" "/tmp/emacs-test-MaJv5k-package/simple-depend-1.0/simple-depend-autoloads.el" "/tmp/emacs-test-MaJv5k-package/simple-two-depend-1.1/simple-two-depend-autoloads.el" "/tmp/emacs-test-u4JGkP-package/simple-single-1.3/simple-single-autoloads.el" "/tmp/emacs-test-CBf8HX-package/simple-single-1.3/simple-single-autoloads.el" "/tmp/emacs-test-NyiQ17-package/simple-single-1.3/simple-single-autoloads.el" "/tmp/emacs-test-4NLfrT-package/multi-file-0.2.3/multi-file-autoloads.el" "/tmp/emacs-test-qZQQde-package/simple-single-1.3/simple-single-autoloads.el" ...))
  :value nil))


--8<---------------cut here---------------end--------------->8---

I am uncertain what the issue is in these cases, but I'll continue
looking around.

bug#59109: 29.0.50; package-tests failing since feature/package+vc merge

[Philip Kaludercic]

"Basil L. Contovounesios" <contovob@tcd.ie> writes:

> Let me know if you'd like me to run anything else on my end.

For some reason I suddenly keep getting `bad-signature' errors that
should (?) be unrelated to the actual issue.  I suspect that there might
be some other misconfiguration on my system.

What I was wondering is if you could run git bisect on the history
between the merge commit and f3e7820b48 to identify where the issues
appeared?

bug#59109: 29.0.50; package-tests failing since feature/package+vc merge

[Philip Kaludercic]

Philip Kaludercic <philipk@posteo.net> writes:

> "Basil L. Contovounesios" <contovob@tcd.ie> writes:
>
>> Let me know if you'd like me to run anything else on my end.
>
> For some reason I suddenly keep getting `bad-signature' errors that
> should (?) be unrelated to the actual issue.  I suspect that there might
> be some other misconfiguration on my system.
>
> What I was wondering is if you could run git bisect on the history
> between the merge commit and f3e7820b48 to identify where the issues
> appeared?

Scrap that, I figured out what the issue was.  package-vc requests
package specifications from "elpa-packages.eld", and I added the file
without adding a signature.  I've generated that, and now all the tests
pass.  The code is still on scratch/package-vc-fixes, as I am still
awaiting a few people to check if other issues have been resolved.  When
that has happened, I'll rebase the changes onto master.

bug#59109: 29.0.50; package-tests failing since feature/package+vc merge

[Stefan Kangas]

Philip Kaludercic <philipk@posteo.net> writes:

> Scrap that, I figured out what the issue was.  package-vc requests
> package specifications from "elpa-packages.eld", and I added the file
> without adding a signature.  I've generated that, and now all the tests
> pass.  The code is still on scratch/package-vc-fixes, as I am still
> awaiting a few people to check if other issues have been resolved.  When
> that has happened, I'll rebase the changes onto master.

That was in November 2022.

Since I'm not currently seeing any test failures, I'm going to assume
this has been fixed, and close this bug.  Please reopen if that's wrong.