#!/bin/sh
# Build every package and an apt repository to serve them from.
#
# Produces three packages:
#   bandsaunter                  the application itself
#   bandsaunter-transcribe       the speech recogniser, which Debian does not
#                                package, vendored into a private directory
#   bandsaunter-model-<name>     the recogniser's model, so a machine never
#                                has to reach the network
#
# The result is a flat apt repository: point a machine at it and
# "apt install bandsaunter" brings the lot, offline from then on.
set -eu

here=$(cd "$(dirname "$0")/.." && pwd)
out=${1:-$here/dist/repo}
model=${MODEL:-base.en}
hf_repo=${HF_REPO:-Systran/faster-whisper-$model}
revision=${DEB_REVISION:-1}
version=$(cd "$here" && python3 -c 'import bandsaunter; print(bandsaunter.debian_version())')

# Compiled wheels tie this to one architecture.  amd64 only, by design.
arch=amd64

mkdir -p "$out"
stage=$(mktemp -d)
trap 'rm -rf "$stage"' EXIT

say() { printf '%s\n' "$*" >&2; }

# ---------------------------------------------------------------------------
say "building bandsaunter ${version}-${revision}"
"$here/packaging/build-deb.sh" "$out" >/dev/null

# ---------------------------------------------------------------------------
say "collecting the speech recogniser (this downloads from PyPI once)"
wheels="$stage/wheels"
mkdir -p "$wheels"
pip download --quiet --only-binary=:all: --dest "$wheels" faster-whisper >&2

pkg="$stage/bandsaunter-transcribe_${version}-${revision}_${arch}"
vendor="$pkg/usr/lib/bandsaunter/vendor"
mkdir -p "$vendor" "$pkg/DEBIAN"
for w in "$wheels"/*.whl; do
    python3 -m zipfile -e "$w" "$vendor/"
done
# Debian already provides these and they win on sys.path anyway, so shipping
# them would be dead weight.
rm -rf "$vendor"/numpy "$vendor"/numpy-* "$vendor"/yaml "$vendor"/PyYAML-* \
       "$vendor"/setuptools "$vendor"/setuptools-* "$vendor"/pkg_resources \
       "$vendor"/_yaml "$vendor"/_distutils_hack "$vendor"/numpy.libs
# A .pth file only runs inside a real site directory; here it is dead weight.
rm -f "$vendor"/*.pth
find "$vendor" -name "__pycache__" -type d -exec rm -rf {} + 2>/dev/null || true

cat > "$pkg/DEBIAN/control" <<EOF
Package: bandsaunter-transcribe
Version: ${version}-${revision}
Section: hamradio
Priority: optional
Architecture: ${arch}
Depends: bandsaunter (= ${version}-${revision}), python3-numpy, python3-yaml
Recommends: bandsaunter-model-$(echo "$model" | tr '._' '--')
Maintainer: bandsaunter
Installed-Size: $(du -ks "$pkg" | cut -f1)
Description: speech recogniser for bandsaunter
 Transcribes recorded voice transmissions to text.
 .
 No speech recogniser is packaged for Debian, so faster-whisper and its
 dependencies are installed here into a private directory rather than into
 dist-packages. That directory is searched after the system one, so anything
 apt provides still takes precedence and these copies only fill the gap.
EOF
fakeroot dpkg-deb --build -Zxz "$pkg" "$out" >/dev/null

# ---------------------------------------------------------------------------
say "collecting the $model model"
modelpkg="$stage/bandsaunter-model-$(echo "$model" | tr '._' '--')_${version}-${revision}_all"
modeldir="$modelpkg/usr/share/bandsaunter/models/$model"
mkdir -p "$modeldir" "$modelpkg/DEBIAN"
PYTHONPATH="$stage/wheels-unused" python3 - "$hf_repo" "$modeldir" <<'PY' >&2
import shutil, sys
from pathlib import Path
from huggingface_hub import snapshot_download
src = Path(snapshot_download(sys.argv[1]))
dst = Path(sys.argv[2])
for item in src.iterdir():
    if item.name.startswith("."):
        continue
    target = dst / item.name
    # Resolve the cache's symlinks so the package holds real files.
    shutil.copy2(item.resolve(), target)
PY

cat > "$modelpkg/DEBIAN/control" <<EOF
Package: bandsaunter-model-$(echo "$model" | tr '._' '--')
Version: ${version}-${revision}
Section: hamradio
Priority: optional
Architecture: all
Depends: bandsaunter-transcribe
Maintainer: bandsaunter
Installed-Size: $(du -ks "$modelpkg" | cut -f1)
Description: $model speech model for bandsaunter
 The $model recognition model, installed locally so that transcription works
 without reaching the network. Without this package the recogniser downloads
 the model the first time it is used, on every machine.
EOF
fakeroot dpkg-deb --build -Zxz "$modelpkg" "$out" >/dev/null

# ---------------------------------------------------------------------------
say "indexing the repository"
( cd "$out" && dpkg-scanpackages --multiversion . /dev/null > Packages 2>/dev/null
  gzip -9kfn Packages
  apt-ftparchive -o APT::FTPArchive::Release::Suite=stable \
                 -o APT::FTPArchive::Release::Codename=bandsaunter \
                 release . > Release )

say ""
say "repository ready: $out"
ls -1sh "$out"/*.deb >&2