Stirling-PDF/Dockerfile
Anthony Stirling 833b3c45c6
Removal of Ghostscript to use qpdf and tesseract directly (#2338)
* navbar fix multi tool and compress location

* release notes and ghostscript removal

* cleanups

* formatting

* update docs

* more

* more

* docs

* release bump

* Hardening suggestions for Stirling-PDF / ghostscript (#2339)

* Protect `readLine()` against DoS

* Sanitized user-provided file names in HTTP multipart uploads

---------

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

---------

Co-authored-by: pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>
2024-11-26 20:50:35 +00:00

68 lines
2.2 KiB
Docker

# Main stage
FROM alpine:3.20.3
# 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 upgrade --no-cache -a && \
apk add --no-cache \
ca-certificates \
tzdata \
tini \
bash \
curl \
qpdf \
shadow \
su-exec \
openssl \
openssl-dev \
openjdk21-jre \
# Doc conversion
libreoffice \
# pdftohtml
poppler-utils \
# OCR MY PDF (unpaper for descew and other advanced features)
tesseract-ocr-data-eng \
# CV
py3-opencv \
# python3/pip
python3 \
py3-pip && \
# uno unoconv and HTML
pip install --break-system-packages --no-cache-dir --upgrade unoconv WeasyPrint pdf2image pillow && \
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
EXPOSE 8080/tcp
# Set user and run command
ENTRYPOINT ["tini", "--", "/scripts/init.sh"]
CMD ["java", "-Dfile.encoding=UTF-8", "-jar", "/app.jar"]