[bug#73660] [PATCH] gexp: Improve support of Unicode characters.

[bug#73660] [PATCH] gexp: Improve support of Unicode characters.

[Tomas Volf]

Support for non-ASCII characters was mixed.  Some gexp forms did support them,
while others did not.  Combined with current value for
%default-port-conversion-strategy, that sometimes led to unpleasant surprises.
For example:

    (scheme-file "utf8" #~(with-output-to-file #$output
                            (λ _ (display "猫"))))

Was written to the store as:

    ((? _ (display "\u732b")))

No, that is not font issue on your part, that is an actual #\? instead of the
lambda character.  Which, surprisingly, does not do what it should when
executed.

The solution is to switch to C.UTF-8 locale where possible, since it is now
always available.  Or to explicitly set the port encoding.

No tests are provided, since majority of tests/gexp.scm use guile in version
2, and it tends to work under it.  The issues occur mostly with guile 3.

I did test it locally using:

      #!/bin/sh
      set -eu
      set -x

      [ -f guix.scm ] || { echo >&2 Run from root of Guix repo.; exit 1; }
      [ -f gnu.scm  ] || { echo >&2 Run from root of Guix repo.; exit 1; }

      cat >猫.scm <<'EOF'
      (define-module (猫)
        #:export (say))

      (define (say)
        "nyaaaa~~~~!")
      EOF

      mkdir -p dir-with-utf8-file
      cp 猫.scm dir-with-utf8-file/

      cat >repro.scm <<'EOF'
      (use-modules (guix build utils)
                   (guix derivations)
                   (guix gexp)
                   (guix store)
                   (ice-9 ftw)
                   (ice-9 textual-ports))

      (define cat "猫")

      (define (drv-content drv)
        (call-with-input-file (derivation->output-path drv)
          get-string-all))

      (define (out-content out)
        (call-with-input-file out
          get-string-all))

      (define (drv-listing drv)
        (scandir (derivation->output-path drv)))

      (define (dir-listing dir)
        (scandir dir))

      (define-macro (test exp lower? report)
        (let ((type (car exp)))
          `(false-if-exception
            (let ((drv (with-store %store
                         (run-with-store %store
                           (,(if lower? lower-object identity) ,exp)))))
              (format #t "~%~a:~%" ',type)
              (when (with-store %store
                      (build-derivations %store (list drv)))
                (format #t "~a~%" (,report drv)))))))

      (test (computed-file "utf8"
                           #~(with-output-to-file #$output
                               (λ _ (display #$cat))))
            #t drv-content)

      (test (program-file "utf8"
                          #~((λ _ (display #$cat))))
            #t drv-content)

      (test (scheme-file "utf8"
                         #~((λ _ (display #$cat))))
            #t drv-content)

      (test (text-file* "utf8" cat cat cat)
            #f drv-content)

      (test (compiled-modules '((猫)))
            #f drv-listing)

      (test (file-union "utf8" `((,cat ,(plain-file "utf8" cat))))
            #t drv-listing)

      ;;; No fix needed:
      (test (imported-modules '((猫)))
            #f dir-listing)

      (test (local-file "dir-with-utf8-file" #:recursive? #t)
            #t dir-listing)

      (test (plain-file "utf8" cat)
            #t out-content)

      (test (mixed-text-file "utf8" cat cat cat)
            #t drv-content)

      (test (directory-union "utf8" (list (local-file "dir-with-utf8-file"
                                                      #:recursive? #t)))
            #t dir-listing)
      EOF

      guix shell -CWN -D guix glibc-locales -- \
           env LANG=C.UTF-8 ./pre-inst-env guix repl -- ./repro.scm

Before this commit, the output is:

      + '[' -f guix.scm ']'
      + '[' -f gnu.scm ']'
      + cat
      + mkdir -p dir-with-utf8-file
      + cp 猫.scm dir-with-utf8-file/
      + cat
      + guix shell -CWN -D guix glibc-locales -- env LANG=C.UTF-8 ./pre-inst-env guix repl -- ./repro.scm

      computed-file:
      ?

      program-file:
      #!/gnu/store/mfkz7fvlfpv3ppwbkv0imb19nrf95akf-guile-3.0.9/bin/guile --no-auto-compile
      !#
      ((? _ (display "\u732b")))

      scheme-file:
      ((? _ (display "\u732b")))

      text-file*:
      ???

      compiled-modules:
      building path(s) `/gnu/store/ay3jifyvliigfgnz67jf0kgngzpya5a5-module-import-compiled'
      Backtrace:
                 5 (primitive-load "/gnu/store/rn7b0dq6iqfmmqyqzamix2mjmfy?")
      In ice-9/eval.scm:
          619:8  4 (_ #f)
      In srfi/srfi-1.scm:
         460:18  3 (fold #<procedure 7ffff79245e0 at ice-9/eval.scm:336:1?> ?)
      In ice-9/eval.scm:
         245:16  2 (_ #(#(#<directory (guix build utils) 7ffff779f320>) # ?))
      In ice-9/boot-9.scm:
        1982:24  1 (_ _)
      In unknown file:
                 0 (stat "./???.scm" #<undefined>)

      ERROR: In procedure stat:
      In procedure stat: No such file or directory: "./???.scm"
      builder for `/gnu/store/dxg87135zcd6a1c92dlrkyvxlbhfwfld-module-import-compiled.drv' failed with exit code 1

      file-union:
      (. .. ?)

      imported-modules:
      (. .. 猫.scm)

      local-file:
      (. .. 猫.scm)

      plain-file:
      猫

      mixed-text-file:
      猫猫猫

      directory-union:
      (. .. 猫.scm)

Which I think you will agree is far from optimal.  After my fix the output
changes to:

      + '[' -f guix.scm ']'
      + '[' -f gnu.scm ']'
      + cat
      + mkdir -p dir-with-utf8-file
      + cp 猫.scm dir-with-utf8-file/
      + cat
      + guix shell -CWN -D guix glibc-locales -- env LANG=C.UTF-8 ./pre-inst-env guix repl -- ./repro.scm

      computed-file:
      猫

      program-file:
      #!/gnu/store/8kbmn359jqkgsbqgqxnmiryvd9ynz8w7-guile-3.0.9/bin/guile --no-auto-compile
      !#
      ((λ _ (display "猫")))

      scheme-file:
      ((λ _ (display "猫")))

      text-file*:
      猫猫猫

      compiled-modules:
      (. .. 猫.go)

      file-union:
      (. .. 猫)

      imported-modules:
      (. .. 猫.scm)

      local-file:
      (. .. 猫.scm)

      plain-file:
      猫

      mixed-text-file:
      猫猫猫

      directory-union:
      (. .. 猫.scm)

Which is actually what the user would expect.

I also added missing arguments to the documentation.

* guix/gexp.scm (computed-file):  Set LANG to C.UTF-8 by default.
(compiled-modules): Try to `setlocale'.
(gexp->script), (gexp->file): New `locale' argument defaulting to C.UTF-8.
(text-file*): Set output port encoding to UTF-8.
* doc/guix.texi (G-Expressions)[computed-file]: Document the changes.  Use
@var.  Document #:guile.
[gexp->script]: Document #:locale.  Fix default value for #:target.
[gexp->file]: Document #:locale, #:system and #:target.

Change-Id: Ib323b51af88a588b780ff48ddd04db8be7c729fb
---
 doc/guix.texi | 11 +++++++----
 guix/gexp.scm | 24 ++++++++++++++++++------
 2 files changed, 25 insertions(+), 10 deletions(-)

diff --git a/doc/guix.texi b/doc/guix.texi
index 52e36e4354..683ba2f44b 100644
--- a/doc/guix.texi
+++ b/doc/guix.texi
@@ -12270,7 +12270,9 @@ G-Expressions
 This is the declarative counterpart of @code{text-file}.
 @end deffn
 
-@deffn {Procedure} computed-file name gexp [#:local-build? #t] [#:options '()]
+@deffn {Procedure} computed-file @var{name} @var{gexp} @
+  [#:local-build? #t] [#:guile] @
+  [#:options '(#:env-vars (("LANG" . "C.UTF-8")))]
 Return an object representing the store item @var{name}, a file or
 directory computed by @var{gexp}.  When @var{local-build?} is true (the
 default), the derivation is built locally.  @var{options} is a list of
@@ -12281,7 +12283,7 @@ G-Expressions
 
 @deffn {Monadic Procedure} gexp->script @var{name} @var{exp} @
   [#:guile (default-guile)] [#:module-path %load-path] @
-  [#:system (%current-system)] [#:target #f]
+  [#:system (%current-system)] [#:target 'current] [#:locale "C.UTF-8"]
 Return an executable script @var{name} that runs @var{exp} using
 @var{guile}, with @var{exp}'s imported modules in its search path.
 Look up @var{exp}'s modules in @var{module-path}.
@@ -12318,8 +12320,9 @@ G-Expressions
 
 @deffn {Monadic Procedure} gexp->file @var{name} @var{exp} @
             [#:set-load-path? #t] [#:module-path %load-path] @
-            [#:splice? #f] @
-            [#:guile (default-guile)]
+            [#:splice? #f] [#:guile (default-guile)] @
+            [#:system (%current-system)] [#:target 'current] @
+            [#:locale "C.UTF-8"]
 Return a derivation that builds a file @var{name} containing @var{exp}.
 When @var{splice?}  is true, @var{exp} is considered to be a list of
 expressions that will be spliced in the resulting file.
diff --git a/guix/gexp.scm b/guix/gexp.scm
index e44aea6420..c8aba91779 100644
--- a/guix/gexp.scm
+++ b/guix/gexp.scm
@@ -597,7 +597,10 @@ (define-record-type <computed-file>
   (options    computed-file-options))             ;list of arguments
 
 (define* (computed-file name gexp
-                        #:key guile (local-build? #t) (options '()))
+                        #:key
+                        guile
+                        (local-build? #t)
+                        (options '(#:env-vars (("LANG" . "C.UTF-8")))))
   "Return an object representing the store item NAME, a file or directory
 computed by GEXP.  When LOCAL-BUILD? is #t (the default), it ensures the
 corresponding derivation is built locally.  OPTIONS may be used to pass
@@ -1700,6 +1703,9 @@ (define* (compiled-modules modules
                        (system base target)
                        (system base compile))
 
+          ;; Best effort.  The locale is not installed in all contexts.
+          (false-if-exception (setlocale LC_ALL "C.UTF-8"))
+
           (define modules
             (getenv "modules"))
 
@@ -1990,7 +1996,8 @@ (define* (gexp->script name exp
                        #:key (guile (default-guile))
                        (module-path %load-path)
                        (system (%current-system))
-                       (target 'current))
+                       (target 'current)
+                       (locale "C.UTF-8"))
   "Return an executable script NAME that runs EXP using GUILE, with EXP's
 imported modules in its search path.  Look up EXP's modules in MODULE-PATH."
   (mlet* %store-monad ((target (if (eq? target 'current)
@@ -2033,7 +2040,8 @@ (define* (gexp->script name exp
                       ;; These derivations are not worth offloading or
                       ;; substituting.
                       #:local-build? #t
-                      #:substitutable? #f)))
+                      #:substitutable? #f
+                      #:env-vars `(("LANG" . ,locale)))))
 
 (define* (gexp->file name exp #:key
                      (guile (default-guile))
@@ -2041,7 +2049,8 @@ (define* (gexp->file name exp #:key
                      (module-path %load-path)
                      (splice? #f)
                      (system (%current-system))
-                     (target 'current))
+                     (target 'current)
+                     (locale "C.UTF-8"))
   "Return a derivation that builds a file NAME containing EXP.  When SPLICE?
 is true, EXP is considered to be a list of expressions that will be spliced in
 the resulting file.
@@ -2081,7 +2090,8 @@ (define* (gexp->file name exp #:key
                           #:local-build? #t
                           #:substitutable? #f
                           #:system system
-                          #:target target)
+                          #:target target
+                          #:env-vars `(("LANG" . ,locale)))
         (gexp->derivation name
                           (gexp
                            (call-with-output-file (ungexp output)
@@ -2098,7 +2108,8 @@ (define* (gexp->file name exp #:key
                           #:local-build? #t
                           #:substitutable? #f
                           #:system system
-                          #:target target))))
+                          #:target target
+                          #:env-vars `(("LANG" . ,locale))))))
 
 (define* (text-file* name #:rest text)
   "Return as a monadic value a derivation that builds a text file containing
@@ -2108,6 +2119,7 @@ (define* (text-file* name #:rest text)
   (define builder
     (gexp (call-with-output-file (ungexp output "out")
             (lambda (port)
+              (set-port-encoding! port "UTF-8")
               (display (string-append (ungexp-splicing text)) port)))))
 
   (gexp->derivation name builder
-- 
2.46.0

[bug#73660] [PATCH] gexp: Improve support of Unicode characters.

[Tomas Volf]

Hello,

any opinion regarding this patch?  I think it prevents whole class of
annoying bugs, and some forms already had support for it, this just
extend it to all forms.

Have a nice day,
Tomas

[bug#73660] [PATCH] gexp: Improve support of Unicode characters.

[Janneke Nieuwenhuizen]

Tomas Volf writes:

Hi,

> any opinion regarding this patch?  I think it prevents whole class of
> annoying bugs, and some forms already had support for it, this just
> extend it to all forms.

While I don't feel qualified to LGTM this patch, it makes sense to me.

As discussed on IRC <https://logs.guix.gnu.org/guix/2025-01-05.log#134213>
I added the patch to core-packages-team, but also reverted it to avoid a
world rebuild.

Just now I pushed a newlyrebased core-packages-team with the patch
in action, see <https://ci.guix.gnu.org/jobset/core-packages-team>.

Would you like to also keep an eye out for how that works?

Greetings,
Janneke

-- 
Janneke Nieuwenhuizen <janneke@gnu.org>  | GNU LilyPond https://LilyPond.org
Freelance IT https://www.JoyOfSource.com | Avatar® https://AvatarAcademy.com

[bug#73660] [PATCH] gexp: Improve support of Unicode characters.

[Tomas Volf]

[-- Attachment #1: Type: text/plain, Size: 1172 bytes --]

Janneke Nieuwenhuizen <janneke@gnu.org> writes:

> Tomas Volf writes:
>
> Hi,
>
>> any opinion regarding this patch?  I think it prevents whole class of
>> annoying bugs, and some forms already had support for it, this just
>> extend it to all forms.
>
> While I don't feel qualified to LGTM this patch, it makes sense to me.
>
> As discussed on IRC <https://logs.guix.gnu.org/guix/2025-01-05.log#134213>
> I added the patch to core-packages-team, but also reverted it to avoid a
> world rebuild.

Re-reading the IRC log I have noticed I forgot to say my thanks, so,
thank you :)

>
> Just now I pushed a newlyrebased core-packages-team with the patch
> in action, see <https://ci.guix.gnu.org/jobset/core-packages-team>.
>
> Would you like to also keep an eye out for how that works?

I can take a look from time to time (seems to still be building).  Let
us hope nothing burns down.  I *think* it should not really break
anything, but who knows, Guix is complex beast and I am not that smart.

Have a nice weekend,
Tomas

-- 
There are only two hard things in Computer Science:
cache invalidation, naming things and off-by-one errors.

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 853 bytes --]

[bug#73660] [PATCH] gexp: Improve support of Unicode characters.

[Tomas Volf]

[-- Attachment #1: Type: text/plain, Size: 2260 bytes --]

Janneke Nieuwenhuizen <janneke@gnu.org> writes:

> Would you like to also keep an eye out for how that works?

It seems the evaluation failed, however I have no idea if that is due to
my changes or not.  The first issue I see in the log seems to be:

--8<---------------cut here---------------start------------->8---
building of `/gnu/store/5qizz7ba86rd979xspsw3vi2xpg6gq7b-glibc-headers-mesboot-2.16.0.drv' timed out after 3600 seconds of silence
--8<---------------cut here---------------end--------------->8---

For what it is worth, it fails to me locally as well, but with a
different error:

--8<---------------cut here---------------start------------->8---
build of /gnu/store/n45z6cfa9i3jdh07q1ib6pcbll8j6jn7-libstdc++-boot0-4.9.4.drv failed
View build log at '/var/log/guix/drvs/n4/5z6cfa9i3jdh07q1ib6pcbll8j6jn7-libstdc++-boot0-4.9.4.drv.gz'.
cannot build derivation `/gnu/store/gai3hg9c8qb89qlz8fwrgpscmf74g6c8-gcc-cross-boot0-14.2.0.drv': 1 dependencies couldn't be built
cannot build derivation `/gnu/store/f2di3rzlyqa2xsby7z197wsldvqixq0l-gcc-cross-boot0-wrapped-14.2.0.drv': 1 dependencies couldn't be built
--8<---------------cut here---------------end--------------->8---

Which, looking into the log leads to:

--8<---------------cut here---------------start------------->8---
starting phase `patch-tzdb.cc'
error: in phase 'patch-tzdb.cc': uncaught exception:
system-error "mkstemp!" "~A" ("No such file or directory") (2) 
phase `patch-tzdb.cc' failed after 0.0 seconds
--8<---------------cut here---------------end--------------->8---

I am not sure this is caused by my changes.  When I revert the commit:

--8<---------------cut here---------------start------------->8---
$ git -C guix-proper log -1
commit 178c8707fc795b7612ed493523a2f4ef5a71966d (HEAD -> xx)
Author: Linux User
Date:   Sat Jan 11 16:56:00 2025 +0000

    Revert "gexp: Improve support of Unicode characters."
    
    This reverts commit 3532efb0167dae540d9b968b191aa76c4ec79212.
--8<---------------cut here---------------end--------------->8---

It still fails with the same error.

Any ideas?

Tomas

-- 
There are only two hard things in Computer Science:
cache invalidation, naming things and off-by-one errors.

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 853 bytes --]

[bug#73660] [PATCH] gexp: Improve support of Unicode characters.

[Janneke Nieuwenhuizen]

Tomas Volf writes:

Hello Tomas,

> Janneke Nieuwenhuizen <janneke@gnu.org> writes:
>
>> Would you like to also keep an eye out for how that works?
>
> It seems the evaluation failed, however I have no idea if that is due to
> my changes or not.  The first issue I see in the log seems to be:
>
> building of
> `/gnu/store/5qizz7ba86rd979xspsw3vi2xpg6gq7b-glibc-headers-mesboot-2.16.0.drv'
> timed out after 3600 seconds of silence

Ah.  I wondered why there was a big red cross instead of a lot of nice
green builds...

> For what it is worth, it fails to me locally as well, but with a
> different error:
>
> build of /gnu/store/n45z6cfa9i3jdh07q1ib6pcbll8j6jn7-libstdc++-boot0-4.9.4.drv failed
> View build log at '/var/log/guix/drvs/n4/5z6cfa9i3jdh07q1ib6pcbll8j6jn7-libstdc++-boot0-4.9.4.drv.gz'.
> cannot build derivation `/gnu/store/gai3hg9c8qb89qlz8fwrgpscmf74g6c8-gcc-cross-boot0-14.2.0.drv': 1 dependencies couldn't be built
> cannot build derivation `/gnu/store/f2di3rzlyqa2xsby7z197wsldvqixq0l-gcc-cross-boot0-wrapped-14.2.0.drv': 1 dependencies couldn't be built
>
>
> Which, looking into the log leads to:
>
> starting phase `patch-tzdb.cc'
> error: in phase 'patch-tzdb.cc': uncaught exception:
> system-error "mkstemp!" "~A" ("No such file or directory") (2) 
> phase `patch-tzdb.cc' failed after 0.0 seconds

Weird!  Oh wait, I removed guards around that stage.

core-packages-team-old has

--8<---------------cut here---------------start------------->8---
          #$@(if (target-hurd64?)
                 #~((add-after 'unpack 'patch-hurd64
                      (lambda _
                        (substitute* "libstdc++-v3/src/c++20/tzdb.cc"
                          (("#if ! defined _GLIBCXX_ZONEINFO_DIR")
                           "#if __GNU__ || ! defined _GLIBCXX_ZONEINFO_DIR")))))
                 '())
          #$@(if (and (target-x86-64?) (target-linux?)
                      (version>=? (package-version gcc) "14"))
                 #~((add-after 'unpack 'patch-x86_64-linux
                      (lambda _
                        (substitute* "libstdc++-v3/src/c++20/tzdb.cc"
                          (("#if ! defined _GLIBCXX_ZONEINFO_DIR")
                           "#if __x86_64__ || ! defined _GLIBCXX_ZONEINFO_DIR")))))
                 '())
          #$@(if (and (target-x86-32?) (target-linux?)
                      (version>=? (package-version gcc) "14"))
                 #~((add-after 'unpack 'patch-x86_64-linux
                      (lambda _
                        (substitute* "libstdc++-v3/src/c++20/tzdb.cc"
                          (("#if ! defined _GLIBCXX_ZONEINFO_DIR")
                           "#if __i386__ || __x86_64__ || ! defined _GLIBCXX_ZONEINFO_DIR")))))
                 '())
          #$@(if (and (target-linux?)
                      (not (target-x86-64?))
                      (not (target-x86-32?))
                      (version>=? (package-version gcc) "14"))
                 #~((add-after 'unpack 'patch-tzdb.cc
                      (lambda _
                        (substitute* "libstdc++-v3/src/c++20/tzdb.cc"
                          (("#if ! defined _GLIBCXX_ZONEINFO_DIR")
                           "#if 1 // ! defined _GLIBCXX_ZONEINFO_DIR")))))
                 '()))
--8<---------------cut here---------------end--------------->8---

and the new core-packages-team has

--8<---------------cut here---------------start------------->8---
          (add-after 'unpack 'patch-tzdb.cc
            (lambda _
              (substitute* "libstdc++-v3/src/c++20/tzdb.cc"
                (("#if ! defined _GLIBCXX_ZONEINFO_DIR")
                 "#if 1 // ! defined _GLIBCXX_ZONEINFO_DIR")))))
--8<---------------cut here---------------end--------------->8---

ow, there it already is.  Silly me, we need the gcc-14 guard.  I was so
happy all systems seemed to need the same code that I also removed the
check for gcc-14.

> I am not sure this is caused by my changes.  When I revert the commit:

Certainly not!  But thanks for trying!

[..]

> Any ideas?

Meanwhile, because it seemed the build farm stopped working for me, I
started to build myself again and currently have

--8<---------------cut here---------------start------------->8---
successfully built /gnu/store/5qizz7ba86rd979xspsw3vi2xpg6gq7b-glibc-headers-mesboot-2.16.0.drv
successfully built /gnu/store/91212rdl4cn4rr8aqfrbilxagmx9fwj3-glibc-mesboot-2.16.0.drv
successfully built /gnu/store/5a0bd35brzf1sgnw10slaxipmxa3cafn-gcc-mesboot1-wrapper-4.6.4.drv
--8<---------------cut here---------------end--------------->8---

so I didn't see this problem yet.  I've pushed a squash! commit that
should fix this.  Thanks!

Greetings,
Janneke

-- 
Janneke Nieuwenhuizen <janneke@gnu.org>  | GNU LilyPond https://LilyPond.org
Freelance IT https://www.JoyOfSource.com | Avatar® https://AvatarAcademy.com

[bug#73660] [PATCH] gexp: Improve support of Unicode characters.

[Ludovic Courtès]

Hello,

Tomas Volf <~@wolfsden.cz> skribis:

> * guix/gexp.scm (computed-file):  Set LANG to C.UTF-8 by default.
> (compiled-modules): Try to `setlocale'.
> (gexp->script), (gexp->file): New `locale' argument defaulting to C.UTF-8.
> (text-file*): Set output port encoding to UTF-8.
> * doc/guix.texi (G-Expressions)[computed-file]: Document the changes.  Use
> @var.  Document #:guile.
> [gexp->script]: Document #:locale.  Fix default value for #:target.
> [gexp->file]: Document #:locale, #:system and #:target.
>
> Change-Id: Ib323b51af88a588b780ff48ddd04db8be7c729fb

[...]

>  (define* (computed-file name gexp
> -                        #:key guile (local-build? #t) (options '()))
> +                        #:key
> +                        guile
> +                        (local-build? #t)
> +                        (options '(#:env-vars (("LANG" . "C.UTF-8")))))

I’d suggest LC_CTYPE (or LC_ALL?) rather than LANG.

Also, what about making it the default for the #:env-vars of
‘gexp->derivation’?  That way it wouldn’t need to be repeated in several
places.

> @@ -1700,6 +1703,9 @@ (define* (compiled-modules modules
>                         (system base target)
>                         (system base compile))
>  
> +          ;; Best effort.  The locale is not installed in all contexts.
> +          (false-if-exception (setlocale LC_ALL "C.UTF-8"))

Sounds good.  I would make it a separate patch.

s/in all contexts/when cross-compiling/

> @@ -1990,7 +1996,8 @@ (define* (gexp->script name exp
>                         #:key (guile (default-guile))
>                         (module-path %load-path)
>                         (system (%current-system))
> -                       (target 'current))
> +                       (target 'current)
> +                       (locale "C.UTF-8"))

I would remove this argument and instead add an explicit, hard-coded:

  (set-port-encoding! port "UTF-8")

in the body of ‘call-with-output-file’ here, just like you did below.

>  (define* (text-file* name #:rest text)
>    "Return as a monadic value a derivation that builds a text file containing
> @@ -2108,6 +2119,7 @@ (define* (text-file* name #:rest text)
>    (define builder
>      (gexp (call-with-output-file (ungexp output "out")
>              (lambda (port)
> +              (set-port-encoding! port "UTF-8")
>                (display (string-append (ungexp-splicing text)) port)))))

LGTM.  This can be moved to a separate file.

How does that sound?

Apologies for not replying earlier!

Ludo’.