Stirling-PDF/Dockerfile.fat

# Build the application
FROM gradle:8.12-jdk17 AS build

# Set the working directory
WORKDIR /app

# Copy the entire project to the working directory
COPY . .

# Build the application with DOCKER_ENABLE_SECURITY=false
RUN DOCKER_ENABLE_SECURITY=true \
STIRLING_PDF_DESKTOP_UI=false \
./gradlew clean build

# Main stage
FROM alpine:3.21.3@sha256:a8560b36e8b8210634f77d9f7f9efd7ffa463e380b75e2e74aff4511df3ef88c

# Copy necessary files
COPY scripts /scripts
COPY pipeline /pipeline
COPY src/main/resources/static/fonts/*.ttf /usr/share/fonts/opentype/noto/
COPY --from=build /app/build/libs/*.jar app.jar

ARG VERSION_TAG

# Set Environment Variables
ENV DOCKER_ENABLE_SECURITY=false \
    VERSION_TAG=$VERSION_TAG \
    JAVA_TOOL_OPTIONS="-XX:+UnlockExperimentalVMOptions \
    -XX:MaxRAMPercentage=75 \
    -XX:InitiatingHeapOccupancyPercent=20 \
    -XX:+G1PeriodicGCInvokesConcurrent \
    -XX:G1PeriodicGCInterval=10000 \
    -XX:+UseStringDeduplication \
    -XX:G1PeriodicGCSystemLoadThreshold=70" \
    HOME=/home/stirlingpdfuser \
    PUID=1000 \
    PGID=1000 \
    UMASK=022 \
    FAT_DOCKER=true \
    INSTALL_BOOK_AND_ADVANCED_HTML_OPS=false \
    PYTHONPATH=/usr/lib/libreoffice/program:/opt/venv/lib/python3.12/site-packages \
    UNO_PATH=/usr/lib/libreoffice/program \
    URE_BOOTSTRAP=file:///usr/lib/libreoffice/program/fundamentalrc


# JDK for app
RUN echo "@main https://dl-cdn.alpinelinux.org/alpine/edge/main" | tee -a /etc/apk/repositories && \
    echo "@community https://dl-cdn.alpinelinux.org/alpine/edge/community" | tee -a /etc/apk/repositories && \
    echo "@testing https://dl-cdn.alpinelinux.org/alpine/edge/testing" | tee -a /etc/apk/repositories && \
    apk upgrade --no-cache -a && \
    apk add --no-cache \
        ca-certificates \
        tzdata \
        tini \
        bash \
        curl \
        shadow \
        su-exec \
        openssl \
        openssl-dev \
        openjdk21-jre \
# Doc conversion
		gcompat \
    	libc6-compat \
        libreoffice \
# pdftohtml
        poppler-utils \
# OCR MY PDF (unpaper for descew and other advanced featues)
        qpdf \
        tesseract-ocr-data-eng \
        
        font-terminus font-dejavu font-noto font-noto-cjk font-awesome font-noto-extra \
# CV
		py3-opencv \
    python3 \
    py3-pip \
    py3-pillow@testing \
    py3-pdf2image@testing && \
    python3 -m venv /opt/venv && \
    export PATH="/opt/venv/bin:$PATH" && \
    pip install --upgrade pip && \
    pip install --no-cache-dir --upgrade unoserver weasyprint && \
    ln -s /usr/lib/libreoffice/program/uno.py /opt/venv/lib/python3.12/site-packages/ && \
    ln -s /usr/lib/libreoffice/program/unohelper.py /opt/venv/lib/python3.12/site-packages/ && \
    ln -s /usr/lib/libreoffice/program /opt/venv/lib/python3.12/site-packages/LibreOffice && \
    mv /usr/share/tessdata /usr/share/tessdata-original && \
    mkdir -p $HOME /configs /logs /customFiles /pipeline/watchedFolders /pipeline/finishedFolders && \
    fc-cache -f -v && \
    chmod +x /scripts/* && \
    chmod +x /scripts/init.sh && \
# User permissions
    addgroup -S stirlingpdfgroup && adduser -S stirlingpdfuser -G stirlingpdfgroup && \
    chown -R stirlingpdfuser:stirlingpdfgroup $HOME /scripts /usr/share/fonts/opentype/noto /configs /customFiles /pipeline && \
    chown stirlingpdfuser:stirlingpdfgroup /app.jar

EXPOSE 8080/tcp
# Set user and run command
ENTRYPOINT ["tini", "--", "/scripts/init.sh"]
CMD ["sh", "-c", "java -Dfile.encoding=UTF-8 -jar /app.jar & /opt/venv/bin/unoserver --port 2003 --interface 0.0.0.0"]