mirror of
https://github.com/Stirling-Tools/Stirling-PDF.git
synced 2026-09-02 21:03:34 +03:00
Anthony Stirling
ddee690c58
# Description of Changes Stirling engine docker slimming Exclude Python virtualenvs from the Docker build context Drop unused provider SDKs from the engine dependency set Retry the SQLite WAL switch when workers race on startup Build the engine image in two stages and run it unprivileged Swap voyage SDK for api call removing 200MB bloat Bundle the AI engine in the fat image Publish the AI engine as a standalone image 886MB to 295MB in docker file And Docker fat is only 230MB bigger after adding (since it already has python and some deps) --- ## Checklist ### General - [ ] I have read the [Contribution Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md) - [ ] I have read the [Stirling-PDF Developer Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/DeveloperGuide.md) (if applicable) - [ ] I have read the [How to add new languages to Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md) (if applicable) - [ ] I have performed a self-review of my own code - [ ] My changes generate no new warnings ### Documentation - [ ] I have updated relevant docs on [Stirling-PDF's doc repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/) (if functionality has heavily changed) - [ ] I have read the section [Add New Translation Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md#add-new-translation-tags) (for new translation tags only) ### Translations (if applicable) - [ ] I ran [`scripts/counter_translation.py`](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/docs/counter_translation.md) ### UI Changes (if applicable) - [ ] Screenshots or videos demonstrating the UI changes are attached (e.g., as comments or direct attachments in the PR) ### Testing (if applicable) - [ ] I have run `task check` to verify linters, typechecks, and tests pass - [ ] I have tested my changes locally. Refer to the [Testing Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/DeveloperGuide.md#7-testing) for more details.
184 lines
8.9 KiB
Docker
184 lines
8.9 KiB
Docker
# syntax=docker/dockerfile:1
|
|
|
|
# Stirling-PDF - Fat version (embedded frontend)
|
|
# Extra fonts for air-gapped environments
|
|
# Uses pre-built base image for fast builds
|
|
|
|
ARG BASE_VERSION=1.0.2@sha256:c7698687f486707ddef9e0298587ca8b44c4e96185e1bdb0c3d119eb2bf9a82e
|
|
ARG BASE_IMAGE=stirlingtools/stirling-pdf-base:${BASE_VERSION}
|
|
|
|
# Stage 1: Build the Java application and frontend
|
|
FROM gradle:9.7.1-jdk25@sha256:a80276ab804c348989df46016e2b5d58cad07c5b29e06f2112434d28ca5b2844 AS app-build
|
|
|
|
ARG TASK_VERSION=3.52.0
|
|
RUN apt-get update \
|
|
&& apt-get install -y --no-install-recommends curl ca-certificates \
|
|
&& update-ca-certificates \
|
|
&& curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \
|
|
&& apt-get install -y --no-install-recommends nodejs \
|
|
&& ARCH=$(dpkg --print-architecture) \
|
|
&& curl -fsSL "https://github.com/go-task/task/releases/download/v${TASK_VERSION}/task_${TASK_VERSION}_linux_${ARCH}.deb" -o /tmp/task.deb \
|
|
&& dpkg -i /tmp/task.deb \
|
|
&& rm /tmp/task.deb \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# JDK 25+: --add-exports is no longer accepted via JAVA_TOOL_OPTIONS; use JDK_JAVA_OPTIONS instead
|
|
ENV JDK_JAVA_OPTIONS="--add-exports=jdk.compiler/com.sun.tools.javac.api=ALL-UNNAMED \
|
|
--add-exports=jdk.compiler/com.sun.tools.javac.file=ALL-UNNAMED \
|
|
--add-exports=jdk.compiler/com.sun.tools.javac.parser=ALL-UNNAMED \
|
|
--add-exports=jdk.compiler/com.sun.tools.javac.tree=ALL-UNNAMED \
|
|
--add-exports=jdk.compiler/com.sun.tools.javac.util=ALL-UNNAMED"
|
|
|
|
WORKDIR /app
|
|
|
|
COPY build.gradle settings.gradle gradlew ./
|
|
COPY gradle/ gradle/
|
|
COPY buildSrc/build.gradle buildSrc/
|
|
COPY buildSrc/src/main/ buildSrc/src/main/
|
|
COPY app/core/build.gradle app/core/
|
|
COPY app/common/build.gradle app/common/
|
|
COPY app/proprietary/build.gradle app/proprietary/
|
|
|
|
# Use system gradle instead of gradlew to avoid SSL issues downloading gradle distribution on emulated arm64
|
|
RUN --mount=type=cache,id=stirling-pdf-gradle-cache,target=/home/gradle/.gradle,sharing=locked \
|
|
gradle dependencies --no-daemon || true
|
|
|
|
COPY . .
|
|
|
|
# Embed the admin portal app at /portal when the deploy workflow flags it.
|
|
ARG BUILD_PORTAL=false
|
|
# Bundle only the JPDFium native for this image's target arch.
|
|
ARG TARGETARCH
|
|
RUN --mount=type=cache,id=stirling-pdf-npm-cache,target=/root/.npm,sharing=locked \
|
|
--mount=type=cache,id=stirling-pdf-gradle-cache,target=/home/gradle/.gradle,sharing=locked \
|
|
JPDFIUM_PLATFORM="$([ "$TARGETARCH" = arm64 ] && echo linux-arm64 || echo linux-x64)" && \
|
|
DISABLE_ADDITIONAL_FEATURES=false \
|
|
gradle clean build \
|
|
-PbuildWithFrontend=true \
|
|
-PbuildWithPortal=${BUILD_PORTAL} \
|
|
-PjpdfiumPlatforms="$JPDFIUM_PLATFORM" \
|
|
-x spotlessApply -x spotlessCheck -x test -x sonarqube \
|
|
--no-daemon
|
|
|
|
# Stage 2: Extract Spring Boot Layers
|
|
FROM eclipse-temurin:25-jre-noble@sha256:fbcf915c585659b30eb766ada4d6d7cfc9ec1040bf521e95bf61b10a25af73db AS jar-extract
|
|
WORKDIR /tmp
|
|
COPY --from=app-build /app/app/core/build/libs/*.jar app.jar
|
|
RUN java -Djarmode=tools -jar app.jar extract --layers --destination /layers
|
|
|
|
|
|
# Stage 2b: AI engine. Built at its final path so the venv resolves after the copy, on uv's
|
|
# managed CPython because the runtime base ships Python 3.12.
|
|
FROM ghcr.io/astral-sh/uv:bookworm-slim@sha256:22334efe746f1b69217d455049b484d7b8cacfb2d5f42555580b62415a98e0a3 AS engine-build
|
|
ENV UV_PYTHON_INSTALL_DIR=/opt/stirling-engine/python
|
|
WORKDIR /opt/stirling-engine
|
|
COPY engine/pyproject.toml engine/uv.lock ./
|
|
# One layer: trimming in a second RUN would cache the untrimmed copy too, and this build
|
|
# exports every layer to a GHA cache that is capped repo-wide. Trimming saves ~20MB.
|
|
RUN --mount=type=cache,target=/root/.cache/uv \
|
|
set -eux; \
|
|
apt-get update && apt-get install -y --no-install-recommends binutils; \
|
|
uv python install 3.13; \
|
|
uv sync --frozen --no-dev --no-install-project --group engine --python-preference only-managed; \
|
|
P="$(ls -d /opt/stirling-engine/python/cpython-*)"; \
|
|
rm -rf "$P/share" "$P/include" \
|
|
"$P/lib/python3.13/idlelib" "$P/lib/python3.13/tkinter" \
|
|
"$P/lib/python3.13/ensurepip" "$P/lib/python3.13/pydoc_data" \
|
|
"$P/lib/python3.13/test" "$P/lib/python3.13/lib2to3"; \
|
|
find /opt/stirling-engine -name '__pycache__' -type d -prune -exec rm -rf {} + ; \
|
|
find /opt/stirling-engine \( -name '*.so' -o -name '*.so.*' \) -print0 \
|
|
| xargs -0 -r strip --strip-unneeded 2>/dev/null || true; \
|
|
apt-get purge -y binutils; apt-get autoremove -y; rm -rf /var/lib/apt/lists/*
|
|
|
|
|
|
# Stage 3: Final runtime image on top of pre-built base
|
|
FROM ${BASE_IMAGE}
|
|
|
|
ARG VERSION_TAG
|
|
|
|
WORKDIR /app
|
|
|
|
# Application layers
|
|
COPY --link --from=jar-extract --chown=1000:1000 /layers/dependencies/ /app/
|
|
COPY --link --from=jar-extract --chown=1000:1000 /layers/spring-boot-loader/ /app/
|
|
COPY --link --from=jar-extract --chown=1000:1000 /layers/snapshot-dependencies/ /app/
|
|
COPY --link --from=jar-extract --chown=1000:1000 /layers/application/ /app/
|
|
|
|
COPY --link --from=app-build --chown=1000:1000 \
|
|
/app/build/libs/restart-helper.jar /restart-helper.jar
|
|
COPY --link --chown=1000:1000 scripts/ /scripts/
|
|
|
|
# init-without-ocr.sh starts the engine when this directory exists, so other images are unaffected.
|
|
COPY --link --from=engine-build --chown=1000:1000 /opt/stirling-engine/python /opt/stirling-engine/python
|
|
COPY --link --from=engine-build --chown=1000:1000 /opt/stirling-engine/.venv /opt/stirling-engine/.venv
|
|
COPY --link --chown=1000:1000 engine/.env /opt/stirling-engine/.env
|
|
COPY --link --chown=1000:1000 engine/src/ /opt/stirling-engine/src/
|
|
|
|
# Fonts go to system dir, root ownership is correct (world-readable)
|
|
COPY app/core/src/main/resources/static/fonts/*.ttf /usr/share/fonts/truetype/
|
|
|
|
# Permissions and configuration
|
|
RUN set -eux; \
|
|
chmod +x /scripts/*; \
|
|
ln -s /logs /app/logs; \
|
|
ln -s /configs /app/configs; \
|
|
ln -s /customFiles /app/customFiles; \
|
|
ln -s /pipeline /app/pipeline; \
|
|
ln -s /storage /app/storage; \
|
|
chown -h stirlingpdfuser:stirlingpdfgroup /app/logs /app/configs /app/customFiles /app/pipeline /app/storage; \
|
|
chown stirlingpdfuser:stirlingpdfgroup /app; \
|
|
mkdir -p /opt/stirling-engine/data; \
|
|
chown -R stirlingpdfuser:stirlingpdfgroup /opt/stirling-engine/data; \
|
|
chmod 750 /tmp/stirling-pdf; \
|
|
chmod 750 /tmp/stirling-pdf/heap_dumps; \
|
|
fc-cache -f
|
|
|
|
# Write version to a file so it is readable by scripts without env-var inheritance.
|
|
RUN echo "${VERSION_TAG:-dev}" > /etc/stirling_version
|
|
|
|
# Environment variables
|
|
ENV VERSION_TAG=$VERSION_TAG \
|
|
STIRLING_AOT_ENABLE="false" \
|
|
STIRLING_JVM_PROFILE="balanced" \
|
|
_JVM_OPTS_BALANCED="-XX:+ExitOnOutOfMemoryError -XX:+HeapDumpOnOutOfMemoryError -XX:HeapDumpPath=/configs/heap_dumps -XX:+UseG1GC -XX:MaxGCPauseMillis=200 -XX:G1HeapRegionSize=4m -XX:G1PeriodicGCInterval=60000 -XX:+UseStringDeduplication -XX:+UseCompactObjectHeaders -XX:+ExplicitGCInvokesConcurrent -Dspring.threads.virtual.enabled=true -Djava.awt.headless=true" \
|
|
_JVM_OPTS_PERFORMANCE="-XX:+ExitOnOutOfMemoryError -XX:+HeapDumpOnOutOfMemoryError -XX:HeapDumpPath=/configs/heap_dumps -XX:+UseShenandoahGC -XX:ShenandoahGCMode=generational -XX:+UseCompactObjectHeaders -XX:+UseStringDeduplication -XX:+AlwaysPreTouch -XX:+ExplicitGCInvokesConcurrent -Dspring.threads.virtual.enabled=true -Djava.awt.headless=true" \
|
|
JAVA_CUSTOM_OPTS="" \
|
|
HOME=/home/stirlingpdfuser \
|
|
PUID=1000 \
|
|
PGID=1000 \
|
|
UMASK=022 \
|
|
FAT_DOCKER=true \
|
|
AIENGINE_ENABLED=true \
|
|
STIRLING_ENGINE_HOME=/opt/stirling-engine \
|
|
STIRLING_ENGINE_PORT=5001 \
|
|
STIRLING_ENGINE_WORKERS=2 \
|
|
INSTALL_BOOK_AND_ADVANCED_HTML_OPS=false \
|
|
STIRLING_TEMPFILES_DIRECTORY=/tmp/stirling-pdf \
|
|
TMPDIR=/tmp/stirling-pdf \
|
|
TEMP=/tmp/stirling-pdf \
|
|
TMP=/tmp/stirling-pdf \
|
|
DBUS_SESSION_BUS_ADDRESS=/dev/null \
|
|
SAL_TMP=/tmp/stirling-pdf/libre
|
|
|
|
# Metadata labels
|
|
LABEL org.opencontainers.image.title="Stirling-PDF Fat" \
|
|
org.opencontainers.image.description="Fat version with extra fonts for air-gapped environments, includes Calibre, LibreOffice, Tesseract, OCRmyPDF" \
|
|
org.opencontainers.image.source="https://github.com/Stirling-Tools/Stirling-PDF" \
|
|
org.opencontainers.image.licenses="MIT" \
|
|
org.opencontainers.image.vendor="Stirling-Tools" \
|
|
org.opencontainers.image.url="https://www.stirlingpdf.com" \
|
|
org.opencontainers.image.documentation="https://docs.stirlingpdf.com" \
|
|
maintainer="Stirling-Tools" \
|
|
org.opencontainers.image.authors="Stirling-Tools" \
|
|
org.opencontainers.image.version="${VERSION_TAG}" \
|
|
org.opencontainers.image.keywords="PDF, manipulation, fat, air-gapped, API, Spring Boot, React"
|
|
|
|
EXPOSE 8080/tcp
|
|
STOPSIGNAL SIGTERM
|
|
|
|
HEALTHCHECK --interval=30s --timeout=15s --start-period=120s --retries=5 \
|
|
CMD curl -fs --max-time 10 http://localhost:8080${SYSTEM_ROOTURIPATH:-''}/api/v1/info/status || exit 1
|
|
|
|
ENTRYPOINT ["tini", "--", "/scripts/init.sh"]
|
|
CMD []
|