8fe9894f65
Older versions of git store the absolute path of the submodules'
repository as stored in the super-project, e.g.:
$ cat some-submodule/.git
gitdir: /path/to/super-project/.git/modules/some-submodule
Obviously, this is not very reproducible.
More recent versions of git, however, store relative paths, which
de-facto makes it reproducible.
Fix older versions by replacing the absolute paths with relative ones.
Signed-off-by: Yann E. MORIN <yann.morin.1998@free.fr>
215 lines
8.0 KiB
Bash
Executable File
215 lines
8.0 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
# We want to catch any unexpected failure, and exit immediately
|
|
set -E
|
|
|
|
# Download helper for git, to be called from the download wrapper script
|
|
#
|
|
# Options:
|
|
# -q Be quiet.
|
|
# -r Clone and archive sub-modules.
|
|
# -o FILE Generate archive in FILE.
|
|
# -u URI Clone from repository at URI.
|
|
# -c CSET Use changeset CSET.
|
|
# -n NAME Use basename NAME.
|
|
#
|
|
# Environment:
|
|
# GIT : the git command to call
|
|
|
|
# Save our path and options in case we need to call ourselves again
|
|
myname="${0}"
|
|
declare -a OPTS=("${@}")
|
|
|
|
# This function is called when an error occurs. Its job is to attempt a
|
|
# clone from scratch (only once!) in case the git tree is borked, or in
|
|
# case an unexpected and unsupported situation arises with submodules
|
|
# or uncommitted stuff (e.g. if the user manually mucked around in the
|
|
# git cache).
|
|
_on_error() {
|
|
local ret=${?}
|
|
|
|
printf "Detected a corrupted git cache.\n" >&2
|
|
if ${BR_GIT_BACKEND_FIRST_FAULT:-false}; then
|
|
printf "This is the second time in a row; bailing out\n" >&2
|
|
exit ${ret}
|
|
fi
|
|
export BR_GIT_BACKEND_FIRST_FAULT=true
|
|
|
|
printf "Removing it and starting afresh.\n" >&2
|
|
|
|
popd >/dev/null
|
|
rm -rf "${git_cache}"
|
|
|
|
exec "${myname}" "${OPTS[@]}" || exit ${ret}
|
|
}
|
|
|
|
verbose=
|
|
recurse=0
|
|
while getopts "${BR_BACKEND_DL_GETOPTS}" OPT; do
|
|
case "${OPT}" in
|
|
q) verbose=-q; exec >/dev/null;;
|
|
r) recurse=1;;
|
|
o) output="${OPTARG}";;
|
|
u) uri="${OPTARG}";;
|
|
c) cset="${OPTARG}";;
|
|
d) dl_dir="${OPTARG}";;
|
|
n) basename="${OPTARG}";;
|
|
:) printf "option '%s' expects a mandatory argument\n" "${OPTARG}"; exit 1;;
|
|
\?) printf "unknown option '%s'\n" "${OPTARG}" >&2; exit 1;;
|
|
esac
|
|
done
|
|
|
|
shift $((OPTIND-1)) # Get rid of our options
|
|
|
|
# Create and cd into the directory that will contain the local git cache
|
|
git_cache="${dl_dir}/git"
|
|
mkdir -p "${git_cache}"
|
|
pushd "${git_cache}" >/dev/null
|
|
|
|
# Any error now should try to recover
|
|
trap _on_error ERR
|
|
|
|
# Caller needs to single-quote its arguments to prevent them from
|
|
# being expanded a second time (in case there are spaces in them)
|
|
_git() {
|
|
eval GIT_DIR="${git_cache}/.git" ${GIT} "${@}"
|
|
}
|
|
|
|
# Create a warning file, that the user should not use the git cache.
|
|
# It's ours. Our precious.
|
|
cat <<-_EOF_ >"${dl_dir}/git.readme"
|
|
IMPORTANT NOTE!
|
|
|
|
The git tree located in this directory is for the exclusive use
|
|
by Buildroot, which uses it as a local cache to reduce bandwidth
|
|
usage.
|
|
|
|
Buildroot *will* trash any changes in that tree whenever it needs
|
|
to use it. Buildroot may even remove it in case it detects the
|
|
repository may have been damaged or corrupted.
|
|
|
|
Do *not* work in that directory; your changes will eventually get
|
|
lost. Do *not* even use it as a remote, or as the source for new
|
|
worktrees; your commits will eventually get lost.
|
|
_EOF_
|
|
|
|
# Initialise a repository in the git cache. If the repository already
|
|
# existed, this is a noop, unless the repository was broken, in which
|
|
# case this magically restores it to working conditions. In the latter
|
|
# case, we might be missing blobs, but that's not a problem: we'll
|
|
# fetch what we need later anyway.
|
|
#
|
|
# We can still go through the wrapper, because 'init' does not use the
|
|
# path pointed to by GIT_DIR, but really uses the directory passed as
|
|
# argument.
|
|
_git init .
|
|
|
|
# Ensure the repo has an origin (in case a previous run was killed).
|
|
if ! _git remote |grep -q -E '^origin$'; then
|
|
_git remote add origin "'${uri}'"
|
|
fi
|
|
|
|
_git remote set-url origin "'${uri}'"
|
|
|
|
printf "Fetching all references\n"
|
|
_git fetch origin
|
|
_git fetch origin -t
|
|
|
|
# Try to get the special refs exposed by some forges (pull-requests for
|
|
# github, changes for gerrit...). There is no easy way to know whether
|
|
# the cset the user passed us is such a special ref or a tag or a sha1
|
|
# or whatever else. We'll eventually fail at checking out that cset,
|
|
# below, if there is an issue anyway. Since most of the cset we're gonna
|
|
# have to clone are not such special refs, consign the output to oblivion
|
|
# so as not to alarm unsuspecting users, but still trace it as a warning.
|
|
if ! _git fetch origin "'${cset}:${cset}'" >/dev/null 2>&1; then
|
|
printf "Could not fetch special ref '%s'; assuming it is not special.\n" "${cset}"
|
|
fi
|
|
|
|
# Check that the changeset does exist. If it does not, re-cloning from
|
|
# scratch won't help, so we don't want to trash the repository for a
|
|
# missing commit. We just exit without going through the ERR trap.
|
|
if ! _git rev-parse --quiet --verify "'${cset}^{commit}'" >/dev/null 2>&1; then
|
|
printf "Commit '%s' does not exist in this repository.\n" "${cset}"
|
|
exit 1
|
|
fi
|
|
|
|
# The new cset we want to checkout might have different submodules, or
|
|
# have sub-dirs converted to/from a submodule. So we would need to
|
|
# deregister _current_ submodules before we checkout.
|
|
#
|
|
# Using "git submodule deinit --all" would remove all the files for
|
|
# all submodules, including the corresponding .git files or directories.
|
|
# However, it was only introduced with git-1.8.3, which is too recent
|
|
# for some enterprise-grade distros.
|
|
#
|
|
# So, we fall-back to just removing all submodules directories. We do
|
|
# not need to be recursive, as removing a submodule will de-facto remove
|
|
# its own submodules.
|
|
#
|
|
# For recent git versions, the repository for submodules is stored
|
|
# inside the repository of the super repository, so the following will
|
|
# only remove the working copies of submodules, effectively caching the
|
|
# submodules.
|
|
#
|
|
# For older versions however, the repository is stored in the .git/ of
|
|
# the submodule directory, so the following will effectively remove the
|
|
# the working copy as well as the repository, which means submodules
|
|
# will not be cached for older versions.
|
|
#
|
|
cmd='printf "Deregistering submodule \"%s\"\n" "${path}" && cd .. && rm -rf "${path##*/}"'
|
|
_git submodule --quiet foreach "'${cmd}'"
|
|
|
|
# Checkout the required changeset, so that we can update the required
|
|
# submodules.
|
|
_git checkout -f -q "'${cset}'"
|
|
|
|
# Get rid of now-untracked directories (in case a git operation was
|
|
# interrupted in a previous run, or to get rid of empty directories
|
|
# that were parents of submodules removed above).
|
|
_git clean -ffdx
|
|
|
|
# Get date of commit to generate a reproducible archive.
|
|
# %cD is RFC2822, so it's fully qualified, with TZ and all.
|
|
date="$( _git log -1 --pretty=format:%cD )"
|
|
|
|
# There might be submodules, so fetch them.
|
|
if [ ${recurse} -eq 1 ]; then
|
|
_git submodule update --init --recursive
|
|
|
|
# Older versions of git will store the absolute path of the git tree
|
|
# in the .git of submodules, while newer versions just use relative
|
|
# paths. Detect and fix the older variants to use relative paths, so
|
|
# that the archives are reproducible across a wider range of git
|
|
# versions. However, we can't do that if git is too old and uses
|
|
# full repositories for submodules.
|
|
cmd='printf "%s\n" "${path}/"'
|
|
for module_dir in $( _git submodule --quiet foreach "'${cmd}'" ); do
|
|
[ -f "${module_dir}/.git" ] || continue
|
|
relative_dir="$( sed -r -e 's,/+,/,g; s,[^/]+/,../,g' <<<"${module_dir}" )"
|
|
sed -r -i -e "s:^gitdir\: $(pwd)/:gitdir\: "${relative_dir}":" "${module_dir}/.git"
|
|
done
|
|
fi
|
|
|
|
# Generate the archive, sort with the C locale so that it is reproducible.
|
|
# We do not want the .git dir; we keep other .git files, in case they are the
|
|
# only files in their directory.
|
|
# The .git dir would generate non reproducible tarballs as it depends on
|
|
# the state of the remote server. It also would generate large tarballs
|
|
# (gigabytes for some linux trees) when a full clone took place.
|
|
find . -not -type d \
|
|
-and -not -path "./.git/*" >"${output}.list"
|
|
LC_ALL=C sort <"${output}.list" >"${output}.list.sorted"
|
|
|
|
# Create GNU-format tarballs, since that's the format of the tarballs on
|
|
# sources.buildroot.org and used in the *.hash files
|
|
tar cf - --transform="s#^\./#${basename}/#" \
|
|
--numeric-owner --owner=0 --group=0 --mtime="${date}" --format=gnu \
|
|
-T "${output}.list.sorted" >"${output}.tar"
|
|
gzip -6 -n <"${output}.tar" >"${output}"
|
|
|
|
rm -f "${output}.list"
|
|
rm -f "${output}.list.sorted"
|
|
|
|
popd >/dev/null
|