Add structured data testing for JSON-LD validation

README.md

@@ -70,6 +70,16 @@ Perform website testing (you must have already [built the site](#build-the-site)
 yarn test
 ```
 
+#### Structured Data Testing
+
+Test structured data (JSON-LD) validation specifically:
+
+```sh
+yarn test-structured-data
+```
+
+This validates that any `application/ld+json` scripts in `build/**/*.html` files have correct schema.org formats and valid JSON syntax.
+
 ## Notes for VS Code
 
 Open this folder in VS Code, allow the "Reopen in Container" and install recommended extensions.

package.json

@@ -10,10 +10,12 @@
     "html-validate": "^10.0.0",
     "markdownlint-cli2": "^0.18.1",
     "prettier": "^3.6.2",
-    "shell-quote": "^1.8.3"
+    "shell-quote": "^1.8.3",
+    "structured-data-testing-tool": "^4.5.0"
   },
   "scripts": {
-    "test": "node test/fixtures-html-validate-should-fail.mjs && node test/build-html-validate.mjs && node test/dirty-words-checker.mjs && node test/dirty-file-paths-checker.mjs",
+    "test": "yarn node test/fixtures-html-validate-should-fail.mjs && yarn node test/fixtures-structured-data-should-fail.mjs && yarn node test/build-html-validate.mjs && yarn node test/dirty-words-checker.mjs && yarn node test/dirty-file-paths-checker.mjs && yarn node test/build-structured-data-validate.mjs",
+    "test-structured-data": "yarn node test/build-structured-data-validate.mjs",
     "lint": "yarn prettier-check && yarn markdownlint-check",
     "lint-fix": "yarn prettier-fix && yarn markdownlint-fix",
     "generate-sitemap": "node scripts/generate-sitemap.mjs",

test/build-structured-data-validate.mjs

@@ -0,0 +1,65 @@
+import { glob } from "glob";
+import { execSync } from "child_process";
+import fs from "fs";
+import path from "path";
+
+// Find and sort all HTML files in the 'build' directory
+const targets = glob.sync("build/**/*.html").sort();
+
+if (targets.length === 0) {
+  console.log("⚠️  No HTML files found in build directory");
+  console.log("   Make sure to build the site first");
+  process.exit(0);
+}
+
+console.log(`🧪 Validating structured data in ${targets.length} files...`);
+
+let hasErrors = false;
+
+// Validate each target file
+for (const target of targets) {
+  try {
+    // Use structured-data-testing-tool CLI to test the file
+    const result = execSync(`yarn dlx structured-data-testing-tool --file "${target}"`, {
+      encoding: "utf8",
+      stdio: "pipe",
+    });
+
+    // Check if there are JSON-LD parse errors or failed tests in the output
+    if (result.includes("Error in jsonld parse") || (result.includes("Failed:") && !result.includes("Failed: 0"))) {
+      console.log("❌ " + target);
+      console.log(result);
+      hasErrors = true;
+    } else {
+      console.log("✅ " + target);
+      // Show a summary of structured data found
+      const lines = result.split("\n");
+      const schemaLine = lines.find((line) => line.includes("Schema.org schemas:"));
+      if (schemaLine && !schemaLine.includes("Schema.org schemas: 0")) {
+        console.log(`    📋 ${schemaLine.trim()}`);
+      }
+      // Only show detailed output if there are warnings
+      if (result.includes("Warnings:") && !result.includes("Warnings: 0")) {
+        console.log("⚠️  Warnings found:");
+        console.log(result);
+      }
+    }
+  } catch (error) {
+    console.log("❌ " + target);
+    console.log("⚠️  Error testing file:", error.message);
+    if (error.stdout) {
+      console.log(error.stdout);
+    }
+    if (error.stderr) {
+      console.error(error.stderr);
+    }
+    hasErrors = true;
+  }
+}
+
+if (hasErrors) {
+  console.log("❌ Some tests failed.");
+  process.exit(1);
+} else {
+  console.log("✨ All tests passed!\n");
+}

test/fixtures-structured-data-should-fail.mjs

@@ -0,0 +1,58 @@
+import { execSync } from "child_process";
+import path from "path";
+
+console.log("🧪 Testing structured data fixtures");
+
+const fixtures = [
+  {
+    file: "test/fixtures/valid-jsonld.html",
+    shouldPass: true,
+    description: "valid JSON-LD",
+  },
+  {
+    file: "test/fixtures/invalid-jsonld.html",
+    shouldPass: false,
+    description: "invalid JSON-LD (syntax error)",
+  },
+];
+
+let allTestsPassed = true;
+
+for (const fixture of fixtures) {
+  try {
+    const result = execSync(`yarn dlx structured-data-testing-tool --file "${fixture.file}"`, {
+      encoding: "utf8",
+      stdio: "pipe",
+    });
+
+    const hasError =
+      result.includes("Error in jsonld parse") || (result.includes("Failed:") && !result.includes("Failed: 0"));
+
+    const actuallyPassed = !hasError;
+
+    if (actuallyPassed === fixture.shouldPass) {
+      console.log(`✅ ${fixture.file}: ${fixture.description} - ${actuallyPassed ? "passed" : "failed"} as expected`);
+    } else {
+      console.error(
+        `❌ ${fixture.file}: ${fixture.description} - expected ${fixture.shouldPass ? "pass" : "fail"} but got ${actuallyPassed ? "pass" : "fail"}`,
+      );
+      console.error("Output:", result);
+      allTestsPassed = false;
+    }
+  } catch (error) {
+    // execSync throws on non-zero exit codes, but structured-data-testing-tool doesn't always exit with error codes
+    console.error(`❌ ${fixture.file}: ${fixture.description} - execution error`);
+    console.error("Error:", error.message);
+    if (error.stdout) {
+      console.error("Stdout:", error.stdout);
+    }
+    allTestsPassed = false;
+  }
+}
+
+if (allTestsPassed) {
+  console.log("✨ All fixtures produced expected results!\n");
+} else {
+  console.error("❌ Some fixture tests failed.");
+  process.exit(1);
+}

test/fixtures/invalid-jsonld.html

@@ -0,0 +1,49 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8">
+    <title>Test page with invalid JSON-LD</title>
+  </head>
+  <body>
+    <h1>Test page with invalid JSON-LD</h1>
+    <p>This page has invalid JSON-LD structured data.</p>
+
+    <script type="application/ld+json">
+      {
+        a"@context": "http://schema.org",
+        "@type": "ReportageNewsArticle",
+        "url": "https://www.bbc.co.uk/news/world-us-canada-49060410",
+        "publisher": {
+          "@type": "NewsMediaOrganization",
+          "name": "BBC News",
+          "publishingPrinciples": "http://www.bbc.co.uk/news/help-41670342",
+          "logo": {
+            "@type": "ImageObject",
+            "url": "https://static.files.bbci.co.uk/ws/simorgh-assets/public/news/images/metadata/poster-1024x576.png"
+          }
+        },
+        "datePublished": "2019-07-20T23:07:27.000Z",
+        "dateModified": "2019-07-21T00:41:12.000Z",
+        "description": "On 20 July 1969, Apollo 11 landed - and hours later Neil Armstrong took his historic first steps.",
+        "headline": "Apollo 11: World celebrates 50th anniversary of first Moon landing",
+        "image": {
+          "@type": "ImageObject",
+          "width": 1200,
+          "height": 675,
+          "url": "https://ichef.bbci.co.uk/ace/branded_news/1200/cpsprodpb/5509/production/_107896712_moonlanding3getty.jpg"
+        },
+        "thumbnailUrl": "https://ichef.bbci.co.uk/ace/branded_news/1200/cpsprodpb/5509/production/_107896712_moonlanding3getty.jpg",
+        "mainEntityOfPage": "https://www.bbc.co.uk/news/world-us-canada-49060410",
+        "author": {
+          "@type": "NewsMediaOrganization",
+          "name": "BBC News",
+          "noBylinesPolicy": "http://www.bbc.co.uk/news/help-41670342#authorexpertise",
+          "logo": {
+            "@type": "ImageObject",
+            "url": "https://static.files.bbci.co.uk/ws/simorgh-assets/public/news/images/metadata/poster-1024x576.png"
+          }
+        }
+      }
+    </script>
+  </body>
+</html>

test/fixtures/valid-jsonld.html

@@ -0,0 +1,49 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8">
+    <title>Test page with valid JSON-LD</title>
+  </head>
+  <body>
+    <h1>Test page with valid JSON-LD</h1>
+    <p>This page has valid JSON-LD structured data.</p>
+
+    <script type="application/ld+json">
+      {
+        "@context": "http://schema.org",
+        "@type": "ReportageNewsArticle",
+        "url": "https://www.bbc.co.uk/news/world-us-canada-49060410",
+        "publisher": {
+          "@type": "NewsMediaOrganization",
+          "name": "BBC News",
+          "publishingPrinciples": "http://www.bbc.co.uk/news/help-41670342",
+          "logo": {
+            "@type": "ImageObject",
+            "url": "https://static.files.bbci.co.uk/ws/simorgh-assets/public/news/images/metadata/poster-1024x576.png"
+          }
+        },
+        "datePublished": "2019-07-20T23:07:27.000Z",
+        "dateModified": "2019-07-21T00:41:12.000Z",
+        "description": "On 20 July 1969, Apollo 11 landed - and hours later Neil Armstrong took his historic first steps.",
+        "headline": "Apollo 11: World celebrates 50th anniversary of first Moon landing",
+        "image": {
+          "@type": "ImageObject",
+          "width": 1200,
+          "height": 675,
+          "url": "https://ichef.bbci.co.uk/ace/branded_news/1200/cpsprodpb/5509/production/_107896712_moonlanding3getty.jpg"
+        },
+        "thumbnailUrl": "https://ichef.bbci.co.uk/ace/branded_news/1200/cpsprodpb/5509/production/_107896712_moonlanding3getty.jpg",
+        "mainEntityOfPage": "https://www.bbc.co.uk/news/world-us-canada-49060410",
+        "author": {
+          "@type": "NewsMediaOrganization",
+          "name": "BBC News",
+          "noBylinesPolicy": "http://www.bbc.co.uk/news/help-41670342#authorexpertise",
+          "logo": {
+            "@type": "ImageObject",
+            "url": "https://static.files.bbci.co.uk/ws/simorgh-assets/public/news/images/metadata/poster-1024x576.png"
+          }
+        }
+      }
+    </script>
+  </body>
+</html>