# check=skip=FromPlatformFlagConstDisallowed
# ^ The --platform=linux/amd64 pins below are DELIBERATE (Exoscale SKS
#   nodes are amd64). BuildKit lints a constant --platform as a smell;
#   here it is the fix. Silenced so a real warning is not lost in noise.
# Bikoret Shoresh Engine — Haskell root activation engine
# Construction spec §1.1: GHC 9.6.4, Cabal 3.10
# Communicates with vav_pipeline via Erlang Port (stdin/stdout)
#
# PLATFORM PIN: see Dockerfile.vav_pipeline for the rationale.
# Exoscale SKS = amd64; arm64 images cannot exec on the cluster.

# === BUILD STAGE ===
FROM --platform=linux/amd64 haskell:9.6.4-slim AS build

# haskell:9.6.4-slim is Debian Buster (EOL) — use archive repos
RUN sed -i 's|deb.debian.org/debian|archive.debian.org/debian|g' /etc/apt/sources.list && \
    sed -i 's|deb.debian.org/debian-security|archive.debian.org/debian-security|g' /etc/apt/sources.list && \
    sed -i '/buster-updates/d' /etc/apt/sources.list && \
    apt-get update && apt-get install -y zlib1g-dev && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Copy cabal files first for dependency caching
COPY shoresh-engine/shoresh-engine.cabal ./
COPY shoresh-engine/cabal.project.freeze ./

RUN cabal update && cabal build --only-dependencies

# Copy source and build
COPY shoresh-engine/ ./

RUN cabal build && \
    cp $(cabal list-bin shoresh-engine) /usr/local/bin/shoresh-engine

# === RUNTIME STAGE ===
FROM --platform=linux/amd64 ubuntu:jammy-20240125

RUN apt-get update && \
    apt-get install -y --no-install-recommends \
      libgmp10 zlib1g locales && \
    rm -rf /var/lib/apt/lists/* && \
    sed -i '/en_US.UTF-8/s/^# //g' /etc/locale.gen && \
    locale-gen

# === UTF-8 IS LOAD-BEARING HERE ===
# This engine's entire job is Hebrew roots. GHC picks stdout's encoding
# from the locale at startup; ubuntu:jammy with no locale set gives the
# POSIX/C locale, i.e. ASCII, and the FIRST non-ASCII byte the engine
# tries to write kills it:
#   Shoresh Engine ...: <stdout>: commitBuffer: invalid argument
#                       (cannot encode character '\8212')
# It died on the em-dash in its own banner, before reading one root.
# vav_pipeline's runtime stage has always set these three; this stage
# did not, and shoresh-engine is the one component that CANNOT run
# without them. Matches Dockerfile.vav_pipeline so both halves of the
# Erlang Port speak the same encoding.
ENV LANG=en_US.UTF-8
ENV LANGUAGE=en_US:en
ENV LC_ALL=en_US.UTF-8

RUN useradd --create-home --shell /bin/bash bikoret
USER bikoret

WORKDIR /home/bikoret

COPY --from=build /usr/local/bin/shoresh-engine ./shoresh-engine

# L1 Torah filesystem — baked into the image
# L1 is read-only in fact, not only in name. Until 2026-10-04 the scroll
# was copied in owned by the service user with its write bits on: the
# process that reads Torah could also have rewritten it, and only the
# SHA-256 check would have noticed afterwards. Owned by root, no write
# bit for anyone; the service user can read and traverse, nothing more.
USER root
COPY --chown=root:root l1/ /mnt/torah/
RUN chmod -R a-w,a+rX /mnt/torah
USER bikoret

# L1 mount point
ENV L1_MOUNT_POINT=/mnt/torah

# The engine is invoked as an Erlang Port by vav_pipeline
# In K8s, it runs as a sidecar or is called via the Port protocol
CMD ["./shoresh-engine"]