(arrow) 07/24: GH-41238: [Release] Use UTF-8 as the default encoding to upload binary (#41242)

[raulcd]

This is an automated email from the ASF dual-hosted git repository.

raulcd pushed a commit to branch maint-16.x.x
in repository https://gitbox.apache.org/repos/asf/arrow.git

commit a1299e23c6ee304f4b8beb7828a0c3b42c1d6c8d
Author: Sutou Kouhei <k...@clear-code.com>
AuthorDate: Wed Apr 17 11:57:58 2024 +0900

    GH-41238: [Release] Use UTF-8 as the default encoding to upload binary 
(#41242)
    
    ### Rationale for this change
    
    We may have non ASCII characters in the process. For example, PGP uid may 
include non ASCII characters.
    
    ### What changes are included in this PR?
    
    Use `LANG=C.UTF-8` and `LC_*=C.UTF-8` to use UTF-8 as the default encoding.
    
    ### Are these changes tested?
    
    Yes. I used this for 16.0.0 RC0.
    
    ### Are there any user-facing changes?
    
    No.
    * GitHub Issue: #41238
    
    Authored-by: Sutou Kouhei <k...@clear-code.com>
    Signed-off-by: Sutou Kouhei <k...@clear-code.com>
---
 dev/release/05-binary-upload.sh | 13 +++++++++++--
 dev/release/binary/runner.sh    | 12 +++++++++++-
 2 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/dev/release/05-binary-upload.sh b/dev/release/05-binary-upload.sh
index ae240c02dd..a45b8fbf8d 100755
--- a/dev/release/05-binary-upload.sh
+++ b/dev/release/05-binary-upload.sh
@@ -21,8 +21,17 @@ set -e
 set -u
 set -o pipefail
 
-export LANG=C
-export LC_CTYPE=C
+export LANG=C.UTF-8
+export LC_ADDRESS=C.UTF-8
+export LC_CTYPE=C.UTF-8
+export LC_IDENTIFICATION=C.UTF-8
+export LC_MEASUREMENT=C.UTF-8
+export LC_MONETARY=C.UTF-8
+export LC_NAME=C.UTF-8
+export LC_NUMERIC=C.UTF-8
+export LC_PAPER=C.UTF-8
+export LC_TELEPHONE=C.UTF-8
+export LC_TIME=C.UTF-8
 
 SOURCE_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 
diff --git a/dev/release/binary/runner.sh b/dev/release/binary/runner.sh
index 465d60d629..76f7bce1ab 100755
--- a/dev/release/binary/runner.sh
+++ b/dev/release/binary/runner.sh
@@ -19,7 +19,17 @@
 
 set -u
 
-export LANG=C
+export LANG=C.UTF-8
+export LC_ADDRESS=C.UTF-8
+export LC_CTYPE=C.UTF-8
+export LC_IDENTIFICATION=C.UTF-8
+export LC_MEASUREMENT=C.UTF-8
+export LC_MONETARY=C.UTF-8
+export LC_NAME=C.UTF-8
+export LC_NUMERIC=C.UTF-8
+export LC_PAPER=C.UTF-8
+export LC_TELEPHONE=C.UTF-8
+export LC_TIME=C.UTF-8
 
 target_dir=/host/binary/tmp
 original_owner=$(stat --format=%u ${target_dir})