818 - Implement an XML sitemap

.github/workflows/publish.yaml

@@ -18,6 +18,24 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'yarn'
+
+      - name: Install dependencies
+        run: yarn install --frozen-lockfile
+
+      - name: Generate sitemap
+        run: yarn generate-sitemap
+        env:
+          # Tags (v*) = production, pushes to main = staging
+          # URLs are resolved from ISAAC_ENV in scripts/sitemap-config.ts,
+          # mirroring the envSpecific() pattern from src/app/services/constants.ts
+          ISAAC_ENV: ${{ startsWith(github.ref, 'refs/tags/') && 'production' || 'staging' }}
+
       - name: Log in to the Container registry
         uses: docker/login-action@v3
         with:

config/webpack.config.cs.js

@@ -39,6 +39,10 @@ module.exports = env => {
                 },{
                     from: resolve('public/robots.txt'),
                     to: 'robots.txt',
+                }, {
+                    from: resolve('public/sitemap.xml'),
+                    to: 'sitemap.xml',
+                    noErrorOnMissing: true, // Sitemap is generated separately so is ok
                 }]
             }),
         ],

package.json

@@ -52,6 +52,7 @@
     "uuid": "^9.0.1"
   },
   "scripts": {
+    "generate-sitemap": "ts-node --project scripts/tsconfig.json scripts/generate-sitemap.ts",
     "build-cs": "webpack --env prod --config config/webpack.config.cs.js",
     "build-dev": "webpack --config config/webpack.config.cs.js",
     "start": "webpack-dev-server --hot --port 8003 --history-api-fallback --config config/webpack.config.cs.js --allowed-hosts=true",
@@ -104,7 +105,9 @@
       }
     }
   },
-  "eslintIgnore": ["/src/IsaacApiTypesAutoGenerated.tsx"],
+  "eslintIgnore": [
+    "/src/IsaacApiTypesAutoGenerated.tsx"
+  ],
   "browserslist": [
     ">0.2%",
     "not dead",
@@ -128,9 +131,11 @@
     "@types/html-to-text": "^9.0.4",
     "@types/jest": "^29.5.12",
     "@types/js-cookie": "^3.0.6",
+    "@types/js-yaml": "^4.0.9",
     "@types/katex": "^0.16.7",
     "@types/leaflet": "^1.9.6",
     "@types/lodash": "^4.17.5",
+    "@types/node": "^20.11.0",
     "@types/object-hash": "^3.0.4",
     "@types/qrcode": "^1.5.2",
     "@types/react-beautiful-dnd": "^13.1.8",
@@ -166,6 +171,7 @@
     "jest": "^29.7.0",
     "jest-environment-jsdom": "^29.7.0",
     "jest-watch-typeahead": "^2.2.2",
+    "js-yaml": "^4.1.1",
     "mini-css-extract-plugin": "^2.9.0",
     "msw": "^1.3.3",
     "prettier": "^3.0.3",
@@ -179,6 +185,7 @@
     "style-loader": "^3.3.4",
     "ts-jest": "^29.4.6",
     "ts-loader": "^9.5.1",
+    "ts-node": "^10.9.2",
     "typescript": "^4.9.5",
     "webpack": "^5.101.3",
     "webpack-bundle-analyzer": "^4.10.2",

public/robots.txt

@@ -9,4 +9,7 @@ Disallow:
 # Allow Googlebot access to everything
 User-agent: Googlebot
 User-agent: Bingbot
-Disallow:
+Disallow:
+
+# Sitemap location
+Sitemap: https://isaaccomputerscience.org/sitemap.xml