Add check that page title is in sync with ToC, h1, and metadata

scripts/js/lib/markdownTitles.test.ts

@@ -0,0 +1,39 @@
+// This code is a Qiskit project.
+//
+// (C) Copyright IBM 2023.
+//
+// This code is licensed under the Apache License, Version 2.0. You may
+// obtain a copy of this license in the LICENSE file in the root directory
+// of this source tree or at http://www.apache.org/licenses/LICENSE-2.0.
+//
+// Any modifications or derivative works of this code must retain this
+// copyright notice, and modified files need to carry a notice indicating
+// that they have been altered from the originals.
+
+import { expect, test } from "@playwright/test";
+
+import { collectHeadingTitleMismatch } from "./markdownTitles";
+
+test("Test to match mismatched titles and headings", async () => {
+  const markdown1 = `
+---
+title: My Awesome Guide
+---
+
+# My Awesome Guide
+    `;
+const markdown2 = `---
+title: Qiskit Doc
+author: John
+---
+
+# Introduction
+
+This guide will walk you through everything.`;
+  const mismatched = await collectHeadingTitleMismatch(markdown1);
+  const mismatched2 = await collectHeadingTitleMismatch(markdown2)
+  const result: string[] = [];
+  const result2: string[] = [`Mismatch: frontmatter title "Qiskit Doc" does not match heading "Introduction"`];
+expect(mismatched).toEqual(result);
+expect(mismatched2).toEqual(result2);
+});

scripts/js/lib/markdownTitles.ts

@@ -0,0 +1,47 @@
+import { unified } from "unified";
+import remarkParse from "remark-parse";
+import remarkGfm from "remark-gfm";
+import remarkFrontmatter from "remark-frontmatter";
+import { visit } from "unist-util-visit";
+import { Root } from "mdast";
+import yaml from "js-yaml";
+
+export async function collectHeadingTitleMismatch(markdown: string): Promise<string[]> {
+  const mismatches: string[] = [];
+  let frontmatterTitle: string | undefined;
+  let headingText: string | undefined;
+
+  const processor = unified()
+    .use(remarkParse)
+    .use(remarkGfm)
+    .use(remarkFrontmatter, ["yaml"]);
+
+  const tree = processor.parse(markdown);
+
+  // Run the transformer manually
+  visit(tree, "yaml", (node: any) => {
+    const data = yaml.load(node.value);
+    if (typeof data === "object" && data !== null && "title" in data) {
+      frontmatterTitle = (data as any).title;
+      console.log("Frontmatter title:", frontmatterTitle);
+    }
+  });
+
+  visit(tree, "heading", (node: any) => {
+    if (node.depth === 1 && !headingText) {
+      headingText = node.children
+        .filter((child: any) => child.type === "text")
+        .map((child: any) => child.value)
+        .join(" ");
+      console.log("Heading text:", headingText);
+    }
+  });
+
+  if (frontmatterTitle && headingText && frontmatterTitle !== headingText) {
+    mismatches.push(
+      `Mismatch: frontmatter title "${frontmatterTitle}" does not match heading "${headingText}"`
+    );
+  }
+
+  return mismatches;
+}