kumquat-buildroot/support/download/git
Maxime Hadjinlian 6d938bcb52 download: git: introduce cache feature
Now we keep the git clone that we download and generates our tarball
from there.
The main goal here is that if you change the version of a package (say
Linux), instead of cloning all over again, you will simply 'git fetch'
from the repo the missing objects, then generates the tarball again.

This should speed the 'source' part of the build significantly.

The drawback is that the DL_DIR will grow much larger; but time is more
important than disk space nowadays.

Signed-off-by: Maxime Hadjinlian <maxime.hadjinlian@gmail.com>
Signed-off-by: Peter Korsgaard <peter@korsgaard.com>
2018-04-02 17:52:53 +02:00

123 lines
4.2 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
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
# 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 ${GIT} "${@}"
}
# We want to check if a cache of the git clone of this repo already exists.
git_cache="${dl_dir}/git"
# If the cache directory doesn't exists, init a new repo, which will be
# fetch'ed later.
if [ ! -d "${git_cache}" ]; then
_git init "'${git_cache}'"
_git -C "'${git_cache}'" remote add origin "'${uri}'"
fi
pushd "${git_cache}" >/dev/null
_git remote set-url origin "'${uri}'"
# Try to fetch with limited depth, since it is faster than a full clone - but
# that only works if the version is a ref (tag or branch). Before trying to do
# a shallow clone we check if ${cset} is in the list provided by git ls-remote.
# If not we fallback to a full fetch.
#
# Messages for the type of clone used are provided to ease debugging in
# case of problems
git_done=0
if [ -n "$(_git ls-remote origin "'${cset}'" 2>&1)" ]; then
printf "Doing a shallow fetch\n"
if _git fetch "${@}" --depth 1 origin "'${cset}'"; then
git_done=1
else
printf "Shallow fetch failed, falling back to fetching all refs\n"
fi
fi
if [ ${git_done} -eq 0 ]; then
printf "Fetching all references\n"
_git fetch origin -t
fi
# Try to get the special refs exposed by some forges (pull-requests for
# github, changes for gerrit...). There is no easy way to know whether
# the cset the user passed us is such a special ref or a tag or a sha1
# or whatever else. We'll eventually fail at checking out that cset,
# below, if there is an issue anyway. Since most of the cset we're gonna
# have to clone are not such special refs, consign the output to oblivion
# so as not to alarm unsuspecting users, but still trace it as a warning.
if ! _git fetch origin "'${cset}:${cset}'" >/dev/null 2>&1; then
printf "Could not fetch special ref '%s'; assuming it is not special.\n" "${cset}"
fi
# Checkout the required changeset, so that we can update the required
# submodules.
_git checkout -q "'${cset}'"
# Get date of commit to generate a reproducible archive.
# %cD is RFC2822, so it's fully qualified, with TZ and all.
date="$( _git log -1 --pretty=format:%cD )"
# There might be submodules, so fetch them.
if [ ${recurse} -eq 1 ]; then
_git submodule update --init --recursive
fi
# Generate the archive, sort with the C locale so that it is reproducible.
# We do not want the .git dir; we keep other .git files, in case they are the
# only files in their directory.
# The .git dir would generate non reproducible tarballs as it depends on
# the state of the remote server. It also would generate large tarballs
# (gigabytes for some linux trees) when a full clone took place.
find . -not -type d \
-and -not -path "./.git/*" >"${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