Add German OCR support to Paperless-ngx

- Created custom Dockerfile extending official paperless-ngx image
- Added tesseract-ocr-deu package for German language OCR
- Set PAPERLESS_OCR_LANGUAGE=deu+eng environment variable
- Updated CI/CD pipeline to build and push custom paperless image
- Modified deployment script to pull paperless image from GHCR
- Tested locally: German (deu) language pack now available alongside English

.github/workflows/ci-cd.yml

@@ -165,7 +165,7 @@ jobs:
           type=ref,event=pr
           type=sha,prefix={{branch}}-
 
-    - name: Build and push Docker image
+    - name: Build and push Docker images
       uses: docker/build-push-action@v5
       with:
         context: ./app
@@ -173,6 +173,14 @@ jobs:
         tags: ${{ steps.meta.outputs.tags }}
         labels: ${{ steps.meta.outputs.labels }}
 
+    - name: Build and push Paperless image
+      uses: docker/build-push-action@v5
+      with:
+        context: ./paperless
+        push: true
+        tags: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-paperless:latest
+        labels: ${{ steps.meta.outputs.labels }}
+
   deploy:
     needs: build
     runs-on: ubuntu-latest
@@ -221,8 +229,8 @@ jobs:
           echo "Attempting to pull images from GitHub Container Registry..."
           if echo $DEPLOY_TOKEN | docker login ghcr.io -u remmerinio --password-stdin; then
             echo "✅ Successfully logged into GHCR"
-            if docker-compose -f compose.yml pull web worker beat; then
-              echo "✅ Successfully pulled web images from GHCR"
+            if docker-compose -f compose.yml pull web worker beat paperless; then
+              echo "✅ Successfully pulled web and paperless images from GHCR"
               USE_REMOTE_IMAGES=true
             else
               echo "⚠️ Failed to pull images from GHCR, will build locally"
@@ -233,14 +241,15 @@ jobs:
             USE_REMOTE_IMAGES=false
           fi
           
-          # Pull other standard images (paperless, redis, postgres, grampsweb)
+          # Pull other standard images (redis, postgres, grampsweb)
           echo "Pulling standard Docker images..."
-          docker-compose -f compose.yml pull db redis paperless grampsweb || echo "Some standard images failed to pull, will use cached versions"
+          docker-compose -f compose.yml pull db redis grampsweb || echo "Some standard images failed to pull, will use cached versions"
           
           # If we couldn't pull from GHCR, build locally
           if [ "$USE_REMOTE_IMAGES" = "false" ]; then
             echo "🔨 Building images locally from source code..."
             docker build -t ghcr.io/remmerinio/stiftung-management-system:latest ./app
+            docker build -t ghcr.io/remmerinio/stiftung-management-system-paperless:latest ./paperless
           fi
           
           # Stop containers and clean up

compose.dev.yml

@@ -54,7 +54,9 @@ services:
     command: ["python", "manage.py", "runserver", "0.0.0.0:8000"]
 
   paperless:
-    image: ghcr.io/paperless-ngx/paperless-ngx:latest
+    build:
+      context: ./paperless
+      dockerfile: Dockerfile
     ports:
       - "8082:8000"
     environment:

compose.yml

@@ -110,7 +110,7 @@ services:
       - redis
 
   paperless:
-    image: ghcr.io/paperless-ngx/paperless-ngx:latest
+    image: ghcr.io/remmerinio/stiftung-management-system-paperless:latest
     ports:
       - "8080:8000"
     environment:

paperless/Dockerfile

@@ -0,0 +1,22 @@
+# Custom Paperless-ngx with German OCR support
+FROM ghcr.io/paperless-ngx/paperless-ngx:latest
+
+# Switch to root to install packages
+USER root
+
+# Update package list and install German OCR language data
+# The correct package name is tesseract-ocr-deu (not tesseract-data-deu)
+RUN apt-get update && \
+    apt-get install -y \
+    tesseract-ocr-deu \
+    && apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Verify German language pack is installed
+RUN tesseract --list-langs | grep deu || echo "German language pack not found"
+
+# Switch back to paperless user
+USER paperless
+
+# Set the OCR language to include German and English
+ENV PAPERLESS_OCR_LANGUAGE=deu+eng