Dockerfile_apache_tika

# Multi-stage build to reduce final image size
# Stage 1: Download Apache Tika JAR
# Override TIKA_VERSION at build time: docker build --build-arg TIKA_VERSION=x.y.z
ARG TIKA_VERSION=3.3.0
FROM docker.io/debian:bookworm-slim AS downloader
ARG TIKA_VERSION

RUN apt-get update -y && \
    apt-get -y install --no-install-recommends ca-certificates curl && \
    curl -fSL -o /tika-server.jar \
        "https://archive.apache.org/dist/tika/${TIKA_VERSION}/tika-server-standard-${TIKA_VERSION}.jar" && \
    chmod 755 /tika-server.jar && \
    apt-get remove -y curl && \
    apt-get clean && \
    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*

# Stage 2: Runtime image with only necessary dependencies
FROM docker.io/debian:bookworm-slim

# Create user and install only runtime dependencies
RUN useradd --system --no-create-home --shell /usr/sbin/nologin gazette && \
    apt-get update -y && \
    apt-get -y install --no-install-recommends \
        default-jre-headless \
        ca-certificates && \
    apt-get clean && \
    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*

# Copy JAR from downloader stage
COPY --from=downloader /tika-server.jar /tika-server.jar

USER gazette
EXPOSE 9998

CMD ["java", "-jar", "/tika-server.jar", "--host", "0.0.0.0"]