# SPDX-FileCopyrightText: 2023 James R. Barlow
# SPDX-License-Identifier: MPL-2.0

FROM alpine:3.22 AS base

ENV LANG=C.UTF-8
ENV TZ=UTC

RUN apk add --no-cache \
    python3 \
    zlib

FROM base AS builder

# Yes it really is python3-dev, and py3-package
RUN apk add --no-cache \
    ca-certificates \
    git \
    python3-dev \
    py3-pyarrow \
    curl

WORKDIR /app

COPY --from=ghcr.io/astral-sh/uv:0.9.8 /uv /uvx /bin/

ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy

RUN uv venv --system-site-packages .venv

# Install the project's dependencies using the lockfile and settings
RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=bind,source=uv.lock,target=uv.lock \
    --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
    uv sync --frozen --no-install-project --no-dev

# Then, add the rest of the project source code and install it
# Installing separately from its dependencies allows optimal layer caching
COPY . /app
RUN --mount=type=cache,target=/root/.cache/uv \
    uv sync --frozen \
        --extra webservice --extra watcher --no-dev \
        --no-install-package pyarrow

FROM base

RUN apk add --no-cache \
    ghostscript \
    jbig2dec \
    jbig2enc \
    pngquant \
    tesseract-ocr \
    tesseract-ocr-data-chi_sim \
    tesseract-ocr-data-deu \
    tesseract-ocr-data-eng \
    tesseract-ocr-data-fra \
    tesseract-ocr-data-osd \
    tesseract-ocr-data-por \
    tesseract-ocr-data-spa \
    font-noto \
    ttf-droid \
    unpaper \
    && rm -rf /var/cache/apk/*

WORKDIR /app

COPY --from=builder --chown=app:app /app /app

RUN rm -rf /app/.git && \
    ln -s /app/misc/webservice.py /app/webservice.py && \
    ln -s /app/misc/watcher.py /app/watcher.py

ENV PATH="/app/.venv/bin:${PATH}"

ENTRYPOINT ["/app/.venv/bin/ocrmypdf"]