buildroot/support/download/dl-wrapper

#!/usr/bin/env bash

# This script is a wrapper to the other download backends.
# Its role is to ensure atomicity when saving downloaded files
# back to BR2_DL_DIR, and not clutter BR2_DL_DIR with partial,
# failed downloads.

# To avoid cluttering BR2_DL_DIR, we download to a trashable
# location, namely in $(BUILD_DIR).
# Then, we move the downloaded file to a temporary file in the
# same directory as the final output file.
# This allows us to finally atomically rename it to its final
# name.
# If anything goes wrong, we just remove all the temporaries
# created so far.

# We want to catch any unexpected failure, and exit immediately.
set -e

# shellcheck source=helpers source-path=SCRIPTDIR
. "${0%/*}/helpers"

export BR_BACKEND_DL_GETOPTS=":hc:d:o:n:N:H:lru:qf:e"

main() {
    local OPT OPTARG
    local backend output large_file recurse quiet rc
    local -a uris hfiles backend_opts post_process_opts

    # Parse our options; anything after '--' is for the backend
    while getopts ":c:d:D:o:n:N:H:lrf:u:qp:P:" OPT; do
        case "${OPT}" in
        c)  cset="${OPTARG}";;
        d)  dl_dir="${OPTARG}";;
        D)  old_dl_dir="${OPTARG}";;
        o)  output="${OPTARG}";;
        n)  raw_base_name="${OPTARG}";;
        N)  base_name="${OPTARG}";;
        H)  hfiles+=( "${OPTARG}" );;
        l)  large_file="-l";;
        r)  recurse="-r";;
        f)  filename="${OPTARG}";;
        u)  uris+=( "${OPTARG}" );;
        p)  post_process="${OPTARG}";;
        P)  post_process_opts+=( "${OPTARG}" );;
        q)  quiet="-q";;
        :)  error "option '%s' expects a mandatory argument\n" "${OPTARG}";;
        \?) error "unknown option '%s'\n" "${OPTARG}";;
        esac
    done

    # Forget our options, and keep only those for the backend
    shift $((OPTIND-1))

    if [ -z "${output}" ]; then
        error "no output specified, use -o\n"
    fi

    # Legacy handling: check if the file already exists in the global
    # download directory. If it does, hard-link it. If it turns out it
    # was an incorrect download, we'd still check it below anyway.
    # If we can neither link nor copy, fallback to doing a download.
    # NOTE! This is not atomic, is subject to TOCTTOU, but the whole
    # dl-wrapper runs under an flock, so we're safe.
    # shellcheck disable=SC2166  # -a works in this case
    if [ ! -e "${output}" -a -e "${old_dl_dir}/${filename}" ]; then
        ln "${old_dl_dir}/${filename}" "${output}" || \
        cp "${old_dl_dir}/${filename}" "${output}" || \
        true
    fi

    # If the output file already exists and:
    # - there's no .hash file: do not download it again and exit promptly
    # - matches all its hashes: do not download it again and exit promptly
    # - fails at least one of its hashes: force a re-download
    # - there's no hash (but a .hash file): consider it a hard error
    if [ -e "${output}" ]; then
        if support/download/check-hash ${quiet} "${output}" "${output##*/}" "${hfiles[@]}"; then
            exit 0
        elif [ ${?} -ne 2 ]; then
            # Do not remove the file, otherwise it might get re-downloaded
            # from a later location (i.e. primary -> upstream -> mirror).
            # Do not print a message, check-hash already did.
            exit 1
        fi
        rm -f "${output}"
        warn "Re-downloading '%s'...\n" "${output##*/}"
    fi

    # Look through all the uris that we were given to download the package
    # source
    download_and_check=0
    rc=1
    for uri in "${uris[@]}"; do
        backend_urlencode="${uri%%+*}"
        backend="${backend_urlencode%|*}"
        case "${backend}" in
            git|svn|cvs|bzr|file|scp|hg|sftp) ;;
            ftp|ftps) backend="curl" ;;
            *) backend="wget" ;;
        esac
        uri=${uri#*+}

        urlencode=${backend_urlencode#*|}
        # urlencode must be "urlencode"
        [ "${urlencode}" != "urlencode" ] && urlencode=""

        # tmpd is a temporary directory in which backends may store
        # intermediate by-products of the download.
        # tmpf is the file in which the backends should put the downloaded
        # content.
        # tmpd is located in $(BUILD_DIR), so as not to clutter the (precious)
        # $(BR2_DL_DIR)
        # We let the backends create tmpf, so they are able to set whatever
        # permission bits they want (although we're only really interested in
        # the executable bit.)
        tmpd="$(mktemp -d "${BUILD_DIR}/.${output##*/}.XXXXXX")"
        tmpf="${tmpd}/output"

        # shellcheck disable=SC2206  # all three are dash-options
        backend_opts=( ${quiet} ${large_file} ${recurse} )
        if [ "${urlencode}" ]; then
            backend_opts+=( -e )
        fi

        # Helpers expect to run in a directory that is *really* trashable, so
        # they are free to create whatever files and/or sub-dirs they might need.
        # Doing the 'cd' here rather than in all backends is easier.
        cd "${tmpd}"

        # If the backend fails, we can just remove the content of the temporary
        # directory to remove all the cruft it may have left behind, and try
        # the next URI until it succeeds. Once out of URI to try, we need to
        # cleanup and exit.
        if ! "${OLDPWD}/support/download/${backend}" \
                -c "${cset}" \
                -d "${dl_dir}" \
                -n "${raw_base_name}" \
                -N "${base_name}" \
                -f "${filename}" \
                -u "${uri}" \
                -o "${tmpf}" \
                "${backend_opts[@]}" \
                -- \
                "${@}"
        then
            # cd back to keep path coherence
            cd "${OLDPWD}"
            rm -rf "${tmpd}"
            continue
        fi

        if [ -n "${post_process}" ] ; then
            if ! "${OLDPWD}/support/download/${post_process}-post-process" \
                    -o "${tmpf}" \
                    -n "${raw_base_name}" \
                    "${post_process_opts[@]}"
            then
                # cd back to keep path coherence
                cd "${OLDPWD}"
                rm -rf "${tmpd}"
                continue
            fi
        fi

        # cd back to free the temp-dir, so we can remove it later
        cd "${OLDPWD}"

        # Check if the downloaded file is sane, and matches the stored hashes
        # for that file
        if support/download/check-hash ${quiet} "${tmpf}" "${output##*/}" "${hfiles[@]}"; then
            rc=0
        else
            if [ ${?} -ne 3 ]; then
                rm -rf "${tmpd}"
                continue
            fi

            # the hash file exists and there was no hash to check the file
            # against
            rc=1
        fi
        download_and_check=1
        break
    done

    # We tried every URI possible, none seems to work or to check against the
    # available hash. *ABORT MISSION*
    if [ "${download_and_check}" -eq 0 ]; then
        rm -rf "${tmpd}"
        exit 1
    fi

    # tmp_output is in the same directory as the final output, so we can
    # later move it atomically.
    tmp_output="$(mktemp "${output}.XXXXXX")"

    # 'mktemp' creates files with 'go=-rwx', so the files are not accessible
    # to users other than the one doing the download (and root, of course).
    # This can be problematic when a shared BR2_DL_DIR is used by different
    # users (e.g. on a build server), where all users may write to the shared
    # location, since other users would not be allowed to read the files
    # another user downloaded.
    # So, we restore the 'go' access rights to a more sensible value, while
    # still abiding by the current user's umask. We must do that before the
    # final 'mv', so just do it now.
    # Some backends (cp and scp) may create executable files, so we need to
    # carry the executable bit if needed.
    [ -x "${tmpf}" ] && new_mode=755 || new_mode=644
    new_mode="$(printf "%04o" $((0${new_mode} & ~0$(umask))))"
    chmod "${new_mode}" "${tmp_output}"

    # We must *not* unlink tmp_output, otherwise there is a small window
    # during which another download process may create the same tmp_output
    # name (very, very unlikely; but not impossible.)
    # Using 'cp' is not reliable, since 'cp' may unlink the destination file
    # if it is unable to open it with O_WRONLY|O_TRUNC; see:
    #   http://pubs.opengroup.org/onlinepubs/9699919799/utilities/cp.html
    # Since the destination filesystem can be anything, it might not support
    # O_TRUNC, so 'cp' would unlink it first.
    # Use 'cat' and append-redirection '>>' to save to the final location,
    # since that is the only way we can be 100% sure of the behaviour.
    if ! cat "${tmpf}" >>"${tmp_output}"; then
        rm -rf "${tmpd}" "${tmp_output}"
        exit 1
    fi
    rm -rf "${tmpd}"

    # tmp_output and output are on the same filesystem, so POSIX guarantees
    # that 'mv' is atomic, because it then uses rename() that POSIX mandates
    # to be atomic, see:
    #   http://pubs.opengroup.org/onlinepubs/9699919799/functions/rename.html
    if ! mv -f "${tmp_output}" "${output}"; then
        rm -f "${tmp_output}"
        exit 1
    fi

    return ${rc}
}

my_name="${0##*/}"
main "${@}"