Dockerfile

# Stage 1: Build the application
FROM sbtscala/scala-sbt:eclipse-temurin-jammy-11.0.17_8_1.9.3_2.13.11 AS builder

WORKDIR /app

# Copy build files
COPY build.sbt .
COPY project ./project

# Download dependencies (cached layer)
RUN sbt update

# Copy source code
COPY src ./src

# Build fat JAR
RUN sbt clean assembly

# Stage 2: Runtime image
FROM eclipse-temurin:11-jre

WORKDIR /app

# Install curl for health checks
RUN apt-get update && apt-get install -y curl && rm -rf /var/lib/apt/lists/*

# Create Flink lib directory for S3 plugin
RUN mkdir -p /opt/flink/lib

# Download Flink S3 Hadoop plugin
RUN curl -L https://repo1.maven.org/maven2/org/apache/flink/flink-s3-fs-hadoop/1.18.0/flink-s3-fs-hadoop-1.18.0.jar \
    -o /opt/flink/lib/flink-s3-fs-hadoop-1.18.0.jar

# Copy the JAR from builder
COPY --from=builder /app/target/scala-2.13/hw3-graphrag-assembly-1.0.jar /app/graphrag.jar

# Copy configuration
COPY src/main/resources/application.conf /app/application.conf
COPY src/main/resources/logback.xml /app/logback.xml

# Create logs directory
RUN mkdir -p /app/logs

# Set FLINK_LIB_DIR so Flink can find the S3 plugin
ENV FLINK_LIB_DIR=/opt/flink/lib

# Default JVM options
ENV JAVA_OPTS="-Xmx2g -Xms512m"

# Expose API port
EXPOSE 8081

# Run the application with classpath pointing to Flink lib
ENTRYPOINT ["sh", "-c", "java $JAVA_OPTS -cp /app/graphrag.jar:/opt/flink/lib/* -Dconfig.file=/app/application.conf -Dlogback.configurationFile=/app/logback.xml Main"]