#!/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
#
# Call it as:
#   .../git [-q] [-r] OUT_FILE REPO_URL CSET BASENAME
#
#   -q  Be quiet.
#   -r  Clone and archive sub-modules.
#
# Environment:
#   GIT      : the git command to call

verbose=
recurse=0
while getopts :qr OPT; do
    case "${OPT}" in
    q)  verbose=-q; exec >/dev/null;;
    r)  recurse=1;;
    \?) printf "unknown option '%s'\n" "${OPTARG}" >&2; exit 1;;
    esac
done
shift $((OPTIND-1))

output="${1}"
repo="${2}"
cset="${3}"
basename="${4}"

shift 4 # 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 ${GIT} "${@}"
}

# Try a shallow clone, 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 ${cset} is in the list provided by git ls-remote. If not
# we fall back on a full clone.
#
# Messages for the type of clone used are provided to ease debugging in case of
# problems
git_done=0
if [ -n "$(_git ls-remote "'${repo}'" "'${cset}'" 2>&1)" ]; then
    printf "Doing shallow clone\n"
    if _git clone ${verbose} "${@}" --depth 1 -b "'${cset}'" "'${repo}'" "'${basename}'"; then
        git_done=1
    else
        printf "Shallow clone failed, falling back to doing a full clone\n"
    fi
fi
if [ ${git_done} -eq 0 ]; then
    printf "Doing full clone\n"
    _git clone ${verbose} "${@}" "'${repo}'" "'${basename}'"
fi

pushd "${basename}" >/dev/null

# 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

# 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.
rm -rf .git

popd >/dev/null

# Generate the archive, sort with the C locale so that it is reproducible
find "${basename}" -not -type d >"${basename}.list"
LC_ALL=C sort <"${basename}.list" >"${basename}.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 - --numeric-owner --owner=0 --group=0 --mtime="${date}" --format=gnu \
         -T "${basename}.list.sorted" >"${output}.tar"
gzip -n <"${output}.tar" >"${output}"