Stirling-PDF/Dockerfile
Anthony Stirling 71e93e3cb5
print (WIP), fake scan (WIP) and text conversion for ultra-lite (#1098)
* Changes!

* lang

* fake scan init, print init and pdf to text for exe

* Hardening suggestions for Stirling-PDF / changes (#1099)

* Switch order of literals to prevent NullPointerException

* Introduced protections against predictable RNG abuse

---------

Co-authored-by: pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>

* Update README.md

* install custom fonts

* Formats etc

* version bump

* disable WIP work

* remove chinese font

---------

Co-authored-by: pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>
Co-authored-by: systo <systo@host.docker.internal>
2024-04-21 23:06:44 +01:00

71 lines
2.3 KiB
Docker

# Main stage
FROM alpine:20240329
# Copy necessary files
COPY scripts /scripts
COPY pipeline /pipeline
COPY src/main/resources/static/fonts/*.ttf /usr/share/fonts/opentype/noto
COPY src/main/resources/static/fonts/*.otf /usr/share/fonts/opentype/noto
COPY build/libs/*.jar app.jar
ARG VERSION_TAG
# Set Environment Variables
ENV DOCKER_ENABLE_SECURITY=false \
VERSION_TAG=$VERSION_TAG \
JAVA_TOOL_OPTIONS="$JAVA_TOOL_OPTIONS -XX:MaxRAMPercentage=75" \
HOME=/home/stirlingpdfuser \
PUID=1000 \
PGID=1000 \
UMASK=022
# JDK for app
RUN echo "@testing https://dl-cdn.alpinelinux.org/alpine/edge/main" | tee -a /etc/apk/repositories && \
echo "@testing 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 update && \
apk add --no-cache \
ca-certificates \
tzdata \
tini \
openssl \
openssl-dev \
bash \
curl \
openjdk17-jre \
su-exec \
shadow \
# Doc conversion
libreoffice@testing \
# pdftohtml
poppler-utils \
# OCR MY PDF (unpaper for descew and other advanced featues)
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 && \
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 && \
tesseract --list-langs && \
rm -rf /var/cache/apk/*
EXPOSE 8080
# Set user and run command
ENTRYPOINT ["tini", "--", "/scripts/init.sh"]
CMD ["java", "-Dfile.encoding=UTF-8", "-jar", "/app.jar"]