Stirling-PDF/DockerfileBase

# Main stage
FROM ubuntu:latest AS base

RUN apt-get update && apt-get install -y --no-install-recommends software-properties-common gnupg2

RUN add-apt-repository ppa:alex-p/tesseract-ocr5 && apt install -y --no-install-recommends tesseract-ocr

RUN apt-get update && \
    apt-get install -y --no-install-recommends \
    	openjdk-17-jre \
        libreoffice-core-nogui \
        libreoffice-common \
        libreoffice-writer-nogui \
        libreoffice-calc-nogui \
        libreoffice-impress-nogui \
        python3-uno \
        ghostscript \
        python3-pip \
        ocrmypdf \
        unoconv && \
    pip install --upgrade pip && \
    pip install --no-cache-dir --user --upgrade ocrmypdf && \
    pip install --no-cache-dir --upgrade pillow==10.0.1 reportlab==3.6.13 wheel==0.38.1 setuptools==65.5.1 pyjwt==2.4.0 cryptography==39.0.1 \
    pip install --no-cache-dir --upgrade ocrmypdf && \
    pip install --no-cache-dir \
        opencv-python-headless && \
    rm -rf /var/lib/apt/lists/* && \
    mkdir /usr/share/tesseract-ocr-original && \
    cp -r /usr/share/tesseract-ocr/* /usr/share/tesseract-ocr-original && \
    rm -rf /usr/share/tesseract-ocr


# Python packages stage
FROM base AS python-packages
# Install build tools and Python libraries
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
        build-essential \
        libffi-dev \
        libssl-dev \
        zlib1g-dev \
        libjpeg-dev 

# Final stage: Copy necessary files from the previous stage
FROM base
COPY --from=python-packages /usr/local /usr/local