818 - Implement an XML sitemap

.github/workflows/publish.yaml

@@ -17,16 +17,33 @@ jobs:
       packages: write
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
+
+      - name: Set up Node.js
+        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
+        with:
+          node-version: '20'
+          cache: 'yarn'
+
+      - name: Install dependencies
+        run: yarn install --frozen-lockfile --ignore-scripts
+
+      - name: Generate sitemap
+        run: yarn generate-sitemap
+        env:
+          # 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
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
       - name: Docker meta cs
         id: meta-cs
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # v5
         with:
           images: ghcr.io/${{ github.repository }}-cs
           tags: |
@@ -36,7 +53,7 @@ jobs:
             type=ref,event=tag
       - name: Docker meta cs-renderer
         id: meta-cs-renderer
-        uses: docker/metadata-action@v5
+        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # v5
         with:
           images: ghcr.io/${{ github.repository }}-cs-renderer
           tags: |
@@ -45,7 +62,7 @@ jobs:
             # tag event
             type=ref,event=tag
       - name: Build and push cs Docker image
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6
         with:
           file: Dockerfile-react
           context: .
@@ -55,7 +72,7 @@ jobs:
           tags: ${{ steps.meta-cs.outputs.tags }}
           labels: ${{ steps.meta-cs.outputs.labels }}
       - name: Build and push cs-renderer Docker image
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6
         with:
           file: Dockerfile-react
           context: .

.github/workflows/update-sitemap.yaml

@@ -0,0 +1,52 @@
+name: Update Sitemap
+
+on:
+  schedule:
+    - cron: "0 6 * * *" # Daily at 06:00 UTC
+  workflow_dispatch: # Allow manual trigger
+
+jobs:
+  update-sitemap:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+
+    steps:
+      - name: Checkout react app
+        uses: actions/checkout@v4
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Checkout content repo
+        uses: actions/checkout@v4
+        with:
+          repository: isaaccomputerscience/isaac-content
+          path: content-repo
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: "20"
+          cache: "yarn"
+
+      - name: Install dependencies
+        run: yarn install --frozen-lockfile --ignore-scripts
+
+      - name: Index content dates
+        run: yarn index-content-dates
+        env:
+          CONTENT_REPO_PATH: ${{ github.workspace }}/content-repo
+
+      - name: Generate sitemap
+        run: yarn generate-sitemap
+        env:
+          ISAAC_ENV: production
+
+      - name: Commit if changed
+        run: |
+          git config user.name  "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+          git add public/sitemap.xml scripts/content-dates.json
+          git diff --cached --quiet || \
+            (git commit -m "chore: update sitemap [skip ci]" && git push)

config/webpack.config.cs.js

@@ -8,7 +8,7 @@ const CopyWebpackPlugin = require('copy-webpack-plugin');
 const { merge } = require('webpack-merge');
 const webpack = require('webpack');
 
-module.exports = env => {
+const webpackConfigCs = env => {
 
     let configCS = {
         entry: {
@@ -39,10 +39,16 @@ 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
                 }]
             }),
         ],
     };
 
     return merge(configCommon(env), configCS);
 };
+
+module.exports = webpackConfigCs;

package.json

@@ -52,6 +52,8 @@
     "uuid": "^9.0.1"
   },
   "scripts": {
+    "generate-sitemap": "ts-node --project scripts/tsconfig.json scripts/generate-sitemap.ts",
+    "index-content-dates": "ts-node --project scripts/tsconfig.json scripts/index-content-dates.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 +106,9 @@
       }
     }
   },
-  "eslintIgnore": ["/src/IsaacApiTypesAutoGenerated.tsx"],
+  "eslintIgnore": [
+    "/src/IsaacApiTypesAutoGenerated.tsx"
+  ],
   "browserslist": [
     ">0.2%",
     "not dead",
@@ -128,9 +132,11 @@
     "@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 +172,7 @@
     "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 +186,7 @@
     "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