build pdftagger.jar from source using maven

Dockerfile

@@ -4,6 +4,7 @@ FROM python:3.12-slim
 RUN apt-get update && apt-get install -y --no-install-recommends \
     tesseract-ocr \
     default-jdk \
+    maven \
     poppler-utils \
     libgl1 \
     libglib2.0-0 \
@@ -23,6 +24,10 @@ RUN pip install --no-cache-dir \
 # Copy source code
 COPY backend/ backend/
 COPY pdf-script/ pdf-script/
+
+# Build the Java tagger JAR from source
+RUN cd pdf-script && mvn package -q -DskipTests && cp target/demo-1.0-SNAPSHOT.jar pdftagger.jar
+
 COPY start.sh /start.sh
 RUN chmod +x /start.sh