Merge branch 'develop' into feature/TED9-166_extend-github-download-packages

Author: schivmeister

requirements.txt

@@ -28,4 +28,4 @@ shortuuid==1.0.13
 pendulum==3.0.0
 saxonche==12.8.0
 elasticsearch-dbapi==0.2.11
-git+https://github.com/meaningfy-ws/mapping-suite-sdk.git@develop
+git+https://github.com/meaningfy-ws/mapping-suite-sdk.git@6912e51999fce515d0175e4e9c2b0c3b4cd6b551

src/infra/ted-sws-stack/README.md

@@ -67,6 +67,7 @@ docker compose -p ted-sws-stack logs -f
 | `.env.testing` | Testing/SRV passwords from Vault (generated by `make testing-unified-dotenv`) |
 | `airflow/Dockerfile` | Airflow image with celery provider |
 | `airflow/requirements.txt` | Python dependencies for Airflow |
+| `fuseki/seed/*.ttl` | Seed data loaded into Fuseki on first startup (one dataset per file) |
 
 ## Environment Configuration
 
@@ -165,6 +166,16 @@ docker volume rm minio-data mongodb-data fuseki-data sftp-data airflow-postgres-
 make start-local-stack
 ```
 
+## Fuseki Seed Data
+
+The `fuseki-init` service runs once on startup (after Fuseki is healthy) and
+idempotently creates datasets from TTL files in `fuseki/seed/`. Each file
+becomes a dataset named after the file (e.g., `test_limes.ttl` → dataset
+`test_limes`). Existing datasets are skipped.
+
+To add a new dataset, drop a `.ttl` file in `fuseki/seed/` and restart the
+stack. No code changes required.
+
 ## Migration from Old Setup
 
 ### Before (old way)

src/infra/ted-sws-stack/airflow/requirements.txt

@@ -28,4 +28,4 @@ shortuuid==1.0.13
 pendulum==3.0.0
 saxonche==12.8.0
 elasticsearch-dbapi==0.2.11
-git+https://github.com/meaningfy-ws/mapping-suite-sdk.git@develop
+git+https://github.com/meaningfy-ws/mapping-suite-sdk.git@6912e51999fce515d0175e4e9c2b0c3b4cd6b551

src/infra/ted-sws-stack/docker-compose.yml

@@ -99,10 +99,50 @@ services:
     restart: unless-stopped
     environment:
       ADMIN_PASSWORD: ${FUSEKI_ADMIN_PASSWORD}
+    healthcheck:
+      test: ["CMD", "wget", "-qO-", "http://localhost:3030/$/ping"]
+      interval: 5s
+      timeout: 5s
+      retries: 10
     networks:
       - internal
       - proxy-net
 
+  fuseki-init:
+    image: curlimages/curl:8.12.1
+    container_name: fuseki-init
+    restart: "no"
+    depends_on:
+      fuseki:
+        condition: service_healthy
+    environment:
+      FUSEKI_ADMIN_PASSWORD: ${FUSEKI_ADMIN_PASSWORD}
+    volumes:
+      - ./fuseki/seed:/seed:ro
+    entrypoint: ["/bin/sh", "-c"]
+    command:
+      - |
+        DATASETS=$$(curl -sf -u "admin:$$FUSEKI_ADMIN_PASSWORD" "http://fuseki:3030/\$$/datasets")
+        for f in /seed/*.ttl; do
+          ds=$$(basename "$$f" .ttl)
+          if echo "$$DATASETS" | grep -q "\"/$${ds}\""; then
+            echo "Dataset $$ds already exists, skipping."
+          else
+            echo "Creating dataset $$ds..."
+            curl -sf -u "admin:$$FUSEKI_ADMIN_PASSWORD" -X POST \
+              "http://fuseki:3030/\$$/datasets" \
+              -d "dbName=$$ds&dbType=tdb2"
+            echo "Loading data into $$ds..."
+            curl -sf -u "admin:$$FUSEKI_ADMIN_PASSWORD" -X POST \
+              "http://fuseki:3030/$$ds/data" \
+              -H "Content-Type: text/turtle" \
+              --data-binary "@$$f" && echo "Loaded $$f into $$ds" || echo "FAIL: could not load $$f"
+          fi
+        done
+        echo "Fuseki init complete."
+    networks:
+      - internal
+
   metabase:
     image: *metabase-version
     container_name: metabase