#!/usr/bin/env bash
# Bootstrap the Arch packaging toolchain (pacman, makepkg, repo-add) on an
# s390x host, then build official Arch PKGBUILDs for s390x.
#
# WHY THIS IS THE KEYSTONE
#
# The README lists "pacman, bash and GNU coreutils are not yet ported" as three
# missing pieces. They are not three tasks -- pacman is the only one that
# matters, because pacman's source tree also ships makepkg and repo-add. Once
# those three run, every remaining package stops being hand-work and becomes
# `makepkg` on the upstream PKGBUILD.
#
# NO CROSS-COMPILATION IS NEEDED HERE. This runs on native s390x hardware, so
# the whole userspace builds at full speed with the host toolchain. That drops
# the z/VM round-trip the other scripts need.
set -euo pipefail

HERE_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
PATCH_DIR="${PATCH_DIR:-$HERE_DIR/../patches/pkgbuild}"
WORK="${WORK:-$HOME/work/arch-s390x}"
REPO="${REPO:-$WORK/repo/s390x}"
PACMAN_GIT="https://gitlab.archlinux.org/pacman/pacman.git"
PKG_GIT_BASE="https://gitlab.archlinux.org/archlinux/packaging/packages"

log() { printf '\n== %s ==\n' "$*"; }

install_host_deps() {
    log "Host build dependencies"
    # Two distinct groups, and confusing them costs hours.
    #
    # makepkg's OWN requirements: bsdtar and fakeroot. Without them it fails
    # deep inside extraction with a bare "bsdtar: command not found".
    #
    # The PKGBUILDs' makedepends: --nodeps tells pacman not to check them, so
    # every one must be satisfied from the Ubuntu host by hand. Each name on
    # the last three lines was added because a build stopped on it --
    # systemtap-sdt-dev and gmp/mpfr/mpc for glibc and gcc, autopoint and
    # gperf for coreutils, asciidoc for pacman, po4a for xz, gnat for gcc's
    # Ada front end, debuginfod and jansson for binutils.
    sudo apt-get -o DPkg::Lock::Timeout=600 install -y -qq \
        meson ninja-build pkg-config gettext \
        libarchive-dev libcurl4-openssl-dev libgpgme-dev libssl-dev \
        libarchive-tools fakeroot \
        build-essential autoconf automake libtool m4 patch texinfo bison flex \
        zstd xz-utils bzip2 \
        systemtap-sdt-dev asciidoc autopoint gperf help2man rsync \
        libgmp-dev libmpfr-dev libmpc-dev python3-docutils \
        libseccomp-dev libpcre2-dev \
        po4a gnat libdebuginfod-dev libjansson-dev
}

build_pacman() {
    log "pacman + makepkg + repo-add"
    mkdir -p "$WORK"
    [ -d "$WORK/pacman" ] || git clone --depth 1 "$PACMAN_GIT" "$WORK/pacman"
    cd "$WORK/pacman"
    # /usr/local, never /usr: this host is Ubuntu and /usr belongs to dpkg.
    # makepkg resolves its own libraries from the configured prefix, so the
    # prefix has to be real -- running it from the build tree fails with
    # "/usr/share/makepkg/*.sh: No such file or directory".
    rm -rf build
    meson setup build --prefix=/usr/local --buildtype=release \
        -Ddoc=disabled -Ddoxygen=disabled -Di18n=false
    ninja -C build -j"$(nproc)"
    sudo ninja -C build install
}

configure_makepkg() {
    log "makepkg configuration"
    # CARCH is already detected as s390x by meson; CHOST must stay the
    # auto-detected triplet -- configure scripts are matched against it, and
    # inventing "s390x-pc-linux-gnu" breaks them.
    sudo sed -i "s|^#\?MAKEFLAGS=.*|MAKEFLAGS=\"-j$(nproc)\"|" /etc/makepkg.conf
    # pacman refuses to initialise alpm without its database directory. The
    # error is only a warning during packaging, but it hides real ones.
    sudo mkdir -p /var/lib/pacman
    # CHOST must be the CANONICAL triplet, not the Debian-style one.
    #
    # gcc -dumpmachine reports s390x-linux-gnu here, but config.sub
    # canonicalises that to s390x-ibm-linux-gnu, and GCC builds its tree
    # under the canonical name. Arch PKGBUILDs assume the canonical form --
    # theirs is x86_64-pc-linux-gnu, with the vendor field present -- so
    # gcc's own PKGBUILD looked for $CHOST/libstdc++-v3/doc and found
    # nothing:
    #
    #   make: *** s390x-linux-gnu/libstdc++-v3/doc: No such file or directory
    #
    # while the build had created s390x-ibm-linux-gnu/libstdc++-v3/doc.
    sudo sed -i 's|^CHOST=.*|CHOST="s390x-ibm-linux-gnu"|' /etc/makepkg.conf
    grep -E '^(CARCH|CHOST|MAKEFLAGS)=' /etc/makepkg.conf
}

# build_package <name> -- fetch the official PKGBUILD and build it for s390x.
#
# --ignorearch: upstream PKGBUILDs carry arch=(x86_64) and nothing else.
# --skipchecksums: GitLab regenerates .patch URLs, so their checksums drift
#   from what the PKGBUILD recorded. Release tarballs still validate; only
#   the generated patches are skipped.
# --nocheck: stage-1 test suites run against the HOST libraries, not Arch's,
#   so their verdict says nothing about the port. acl failed its check() on a
#   perfectly sound build, and the suites cost hours. Stage 2 runs them.
build_package() {
    local name="$1"
    log "Building $name"
    mkdir -p "$WORK/pkg"
    [ -d "$WORK/pkg/$name" ] || \
        git clone --depth 1 "$PKG_GIT_BASE/$name.git" "$WORK/pkg/$name"
    cd "$WORK/pkg/$name"
    # Port patches. Upstream PKGBUILDs are written for x86_64 and some carry
    # flags no other architecture accepts -- glibc's --enable-sframe is the
    # first. They are applied here, one hook per package, so each change is
    # visible, reviewable and survives a re-clone, rather than being an edit
    # someone once made by hand in a working copy.
    local hook="$PATCH_DIR/$name.sh"
    if [ -f "$hook" ]; then
        git checkout -- PKGBUILD 2>/dev/null || true
        bash "$hook" || return 1
    fi
    rm -f ./*.pkg.tar.*
    # Explicit `|| return 1`. Relying on `set -e` here does NOT work: callers
    # invoke build_package inside `if`, which disables set -e for the whole
    # function body. A failing makepkg then fell through to repo-add, whose
    # success became the function's exit status -- and a run reported
    # "51 built, 0 failed" while glibc, gcc, coreutils and pacman had all
    # failed. Measured: the repository held 23 files, not a hundred.
    makepkg --nodeps --ignorearch --skippgpcheck --skipchecksums --nocheck -f \
        || return 1
    # An exit code is not proof. Only the artefact is.
    local produced=()
    shopt -s nullglob
    produced=(./*.pkg.tar.*)
    shopt -u nullglob
    if [ "${#produced[@]}" -eq 0 ]; then
        echo "no package produced for $name" >&2
        return 1
    fi
    mkdir -p "$REPO"
    cp -f "${produced[@]}" "$REPO/" || return 1
    # Only the new packages. Globbing the whole repository made repo-add
    # re-index everything on every call: quadratic, and it buried the real
    # lines under warnings about entries that already existed.
    local names=() f
    for f in "${produced[@]}"; do names+=("$(basename "$f")"); done
    ( cd "$REPO" && repo-add core.db.tar.gz "${names[@]}" ) || return 1
}

main() {
    install_host_deps
    build_pacman
    configure_makepkg
    for p in "$@"; do build_package "$p"; done
    log "Done"
    command -v pacman makepkg repo-add
}

# Only run when executed, never when sourced: build-stage1.sh reuses
# build_package and must not re-run the whole bootstrap to get it.
if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
    main "$@"
fi