Merge pull request #6 from bacpop/bacpop-197-species-old-projects

Bacpop-197 Add Data migration to set default species to pneumo

.github/workflows/Pytest.yml

@@ -2,8 +2,6 @@ on:
   push:
     branches:
       - main
-      - master
-      - "bacpop-*"
   pull_request:
     branches:
       - main

README.md

@@ -34,3 +34,14 @@ We have one copy of `beebop` deployed:
 * server: `beebop.dide.ic.ac.uk`
 * config: `prod.yml`
 * command to run: `./beebop start prod`
+
+### Running data migrations
+
+All data migrations are stored in the migration folder in the server. The naming convention is `YYYYMMDDHHMMSS_<migration_name>.sh`.
+
+To run them, you can use the following command from the **root**, and replace the migration file with the one you want to run:
+
+```bash
+docker exec beebop-redis bash -c "$(cat ./migrations/<migration_file>)"
+
+```

migrations/20241008_default_species.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+set -eu
+
+# This script will set the species field to "Streptococcus pneumoniae" for all projects in the database
+
+projectKeys=$(redis-cli --scan | grep -E ^beebop:project:[a-zA-Z0-9]+$)
+
+
+echo "Number of found projects: $(echo "$projectKeys" | wc -w)"
+
+for key in $projectKeys; do
+    currentSpecies=$(redis-cli HGET "$key" species)
+    if [ -z "$currentSpecies" ]; then
+        redis-cli HSET "$key" species "Streptococcus pneumoniae"
+    fi
+done

src/beebop_deploy.py

@@ -173,7 +173,7 @@ def api_configure(container, cfg):
         print("[api] Storage db already exists, doing nothing")
     else:
         print("[api] Downloading storage database")
-        args = ["./scripts/download_db"]
+        args = ["./scripts/download_databases"]
         mounts = [docker.types.Mount("/beebop/storage",
                   cfg.volumes["storage"])]
         container.client.containers.run(str(cfg.api_ref), args, mounts=mounts,