init: integrate MusicOCR workspace base

.github/workflows/backup.yml

@@ -0,0 +1,25 @@
+name: Backup Data Repo
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "0 2 * * *"
+
+jobs:
+  backup:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+        with:
+          lfs: true
+
+      - name: Create archive
+        run: |
+          tar -czf musicocr-data-repo.tgz projects campaigns manifests .gitattributes
+
+      - name: Upload archive artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: musicocr-data-repo-backup
+          path: musicocr-data-repo.tgz

.github/workflows/validate.yml

@@ -0,0 +1,44 @@
+name: Validate Data Repo
+
+on:
+  push:
+  workflow_dispatch:
+
+jobs:
+  validate:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+        with:
+          lfs: true
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Validate JSON files
+        run: |
+          python - <<'PY'
+          import json
+          from pathlib import Path
+
+          json_files = list(Path(".").rglob("*.json"))
+          bad = []
+          for path in json_files:
+              try:
+                  json.loads(path.read_text(encoding="utf-8"))
+              except Exception as exc:
+                  bad.append(f"{path}: {exc}")
+
+          if bad:
+              raise SystemExit("Invalid JSON files:\n" + "\n".join(bad))
+
+          print(f"Validated {len(json_files)} JSON files.")
+          PY
+
+      - name: Check required top-level folders
+        run: |
+          test -d projects
+          test -d manifests

manifests/access_control.example.json

@@ -0,0 +1,31 @@
+{
+  "schema_version": "1.0",
+  "users": {
+    "admin@example.org": {
+      "role": "admin",
+      "github_logins": ["komisla"],
+      "all_projects": true,
+      "can_create_projects": true
+    },
+    "reviewer@example.org": {
+      "role": "viewer",
+      "projects": [
+        {
+          "name": "Bach-Singet-dem-Herrn",
+          "access": "read"
+        }
+      ]
+    },
+    "annotator@example.org": {
+      "role": "editor",
+      "projects": [
+        {
+          "name": "Bach-Singet-dem-Herrn",
+          "access": "write",
+          "pages": [1, 2, 3],
+          "sections": ["alto", "tenor"]
+        }
+      ]
+    }
+  }
+}

manifests/access_control.json

@@ -0,0 +1,4 @@
+{
+  "schema_version": "1.0",
+  "users": {}
+}

manifests/repo_manifest.json

@@ -0,0 +1,7 @@
+{
+  "schema_version": "1.0",
+  "repo_type": "musicocr_data_repo",
+  "projects_root": "projects",
+  "campaigns_root": "campaigns",
+  "access_control_file": "manifests/access_control.json"
+}