This is an automated email from the ASF dual-hosted git repository.
kou pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow.git
The following commit(s) were added to refs/heads/main by this push:
new 3575360736 GH-47081: [Release] Verify reproducible source build
explicitly (#47082)
3575360736 is described below
commit 35753607366d60b2e8aaf2858d12a91940d65426
Author: Sutou Kouhei <[email protected]>
AuthorDate: Sun Jul 13 20:29:11 2025 +0900
GH-47081: [Release] Verify reproducible source build explicitly (#47082)
### Rationale for this change
There are 2 problems on verification of reproducible source archive:
1. CI on macOS isn't prepared correctly
2. Some verification environments may not have required tools
FYI: We need the following to check reproducible build on macOS:
* Ensure using apache/arrow for `GITHUB_REPOSITORY`
* `GITHUB_REPOSITORY` is defined automatically on GitHub Actions. Our
Crossbow based verification job has `GITHUB_REPOSITORY=ursacomputing/crossbow`
by default.
* GNU tar
* GNU gzip
### What changes are included in this PR?
For the problem1:
* Set `GITHUB_REPOSITORY` explicitly
* Install GNU gzip (GNU tar is already installed)
For the problem2:
* Add `TEST_SOURCE_REPRODUCIBLE` that is `0` by default
* Set `TEST_SOURCE_REPRODUCIBLE=1` on CI
* At least one PMC member must set `TEST_SOURCE_REPRODUCIBLE=1` on release
verification
### Are these changes tested?
Yes.
### Are there any user-facing changes?
No.
* GitHub Issue: #47081
Authored-by: Sutou Kouhei <[email protected]>
Signed-off-by: Sutou Kouhei <[email protected]>
---
dev/release/verify-release-candidate.sh | 30 +++++++++++++++++------
dev/tasks/verify-rc/github.linux.amd64.docker.yml | 3 +++
dev/tasks/verify-rc/github.macos.yml | 17 ++++++++++++-
3 files changed, 41 insertions(+), 9 deletions(-)
diff --git a/dev/release/verify-release-candidate.sh
b/dev/release/verify-release-candidate.sh
index 28e4ed247d..b38da36c38 100755
--- a/dev/release/verify-release-candidate.sh
+++ b/dev/release/verify-release-candidate.sh
@@ -789,14 +789,6 @@ ensure_source_directory() {
if [ ! -d "${ARROW_SOURCE_DIR}" ]; then
pushd $ARROW_TMPDIR
fetch_archive ${dist_name}
- git clone https://github.com/${GITHUB_REPOSITORY}.git arrow
- pushd arrow
- dev/release/utils-create-release-tarball.sh ${VERSION} ${RC_NUMBER}
- if ! cmp ${dist_name}.tar.gz ../${dist_name}.tar.gz; then
- echo "Source archive isn't reproducible"
- return 1
- fi
- popd
tar xf ${dist_name}.tar.gz
popd
fi
@@ -845,6 +837,27 @@ test_source_distribution() {
pushd $ARROW_SOURCE_DIR
+ if [ "${SOURCE_KIND}" = "tarball" ] && [ "${TEST_SOURCE_REPRODUCIBLE}" -gt 0
]; then
+ pushd ..
+ git clone "https://github.com/${GITHUB_REPOSITORY}.git"; arrow
+ pushd arrow
+ dev/release/utils-create-release-tarball.sh "${VERSION}" "${RC_NUMBER}"
+ tarball="apache-arrow-${VERSION}.tar.gz"
+ if ! cmp "${tarball}" "../${tarball}"; then
+ echo "Source archive isn't reproducible"
+ if ! tar --version | grep --quiet --fixed GNU && \
+ ! gtar --version | grep --quiet --fixed GNU; then
+ echo "We need GNU tar to verify reproducible build"
+ fi
+ if ! gzip --version | grep --quiet --fixed GNU; then
+ echo "We need GNU gzip to verify reproducible build"
+ fi
+ return 1
+ fi
+ popd
+ popd
+ fi
+
if [ ${TEST_CSHARP} -gt 0 ]; then
test_csharp
fi
@@ -1033,6 +1046,7 @@ test_wheels() {
: ${TEST_YUM:=${TEST_BINARIES}}
# Source verification tasks
+: ${TEST_SOURCE_REPRODUCIBLE:=0}
: ${TEST_CPP:=${TEST_SOURCE}}
: ${TEST_CSHARP:=${TEST_SOURCE}}
: ${TEST_GLIB:=${TEST_SOURCE}}
diff --git a/dev/tasks/verify-rc/github.linux.amd64.docker.yml
b/dev/tasks/verify-rc/github.linux.amd64.docker.yml
index 97eecd2d28..dd5fd9f891 100644
--- a/dev/tasks/verify-rc/github.linux.amd64.docker.yml
+++ b/dev/tasks/verify-rc/github.linux.amd64.docker.yml
@@ -52,6 +52,9 @@ jobs:
{% endif %}
-e VERIFY_RC="{{ rc|default("") }}" \
-e TEST_DEFAULT=0 \
+ {% if target == "cpp" %}
+ -e TEST_SOURCE_REPRODUCIBLE=1 \
+ {% endif %}
-e TEST_{{ target|upper }}=1 \
{{ distro }}-verify-rc
diff --git a/dev/tasks/verify-rc/github.macos.yml
b/dev/tasks/verify-rc/github.macos.yml
index 93486f4604..315083543c 100644
--- a/dev/tasks/verify-rc/github.macos.yml
+++ b/dev/tasks/verify-rc/github.macos.yml
@@ -59,6 +59,9 @@ jobs:
if [ -x "${pkgconf}" ]; then
echo "PKG_CONFIG=${pkgconf}" >> $GITHUB_ENV
fi
+
+ # For reproducible source archive verification
+ brew install gzip
{% endif %}
- uses: actions/setup-java@v2
@@ -91,6 +94,18 @@ jobs:
USE_CONDA: 1
{% else %}
GTest_SOURCE: SYSTEM
+ {% if target == "cpp" %}
+ TEST_SOURCE_REPRODUCIBLE: 1
+ {% endif %}
{% endif %}
run: |
- arrow/dev/release/verify-release-candidate.sh {{ release|default("")
}} {{ rc|default("") }}
+ version={{ release|default("") }}
+ rc={{ rc|default("") }}
+ if [ -n "${version}" ] && [ -n "${rc}" ]; then
+ args=("${version}" "${rc}")
+ GITHUB_REPOSITORY=apache/arrow
+ else
+ args=()
+ GITHUB_REPOSITORY={{ arrow.github_repo }}
+ fi
+ arrow/dev/release/verify-release-candidate.sh "${args[@]}"
