# Main stage
FROM alpine:3.19.0

# JDK for app
RUN apk add --no-cache \
        ca-certificates \
        tzdata \
        tini \
        bash \
        curl \
        openjdk17-jre && \
# Doc conversion
    apk add --no-cache libreoffice --repository http://dl-cdn.alpinelinux.org/alpine/edge/community && \
# OCR MY PDF (unpaper for descew and other advanced featues)
    apk add --no-cache \
        ocrmypdf \
        tesseract-ocr-data-eng \
# CV
        py3-opencv \
# python3/pip
        python3 && \
    wget https://bootstrap.pypa.io/get-pip.py -qO - | python3 - --break-system-packages --no-cache-dir --upgrade && \
# uno unoconv and HTML
    pip install --break-system-packages --no-cache-dir --upgrade unoconv WeasyPrint && \
    mv /usr/share/tessdata /usr/share/tessdata-original