fix(seo): honour SITE_URL for blog canonicals (#933)

A build with a custom SITE_URL failed seo-audit on the blog pages:
generate-blog.mjs hard-coded https://www.bentopdf.com, and the
hand-written blog/author-alam.html carries that origin literally while
generate-i18n-pages.mjs only rewrites top-level pages.

generate-blog.mjs now reads SITE_URL like its sibling scripts, and
enhance-seo-pages.mjs rebases the default origin in dist/blog/*.html
to SITE_URL (dist only, no-op for the default URL) through a small
side-effect-free helper, scripts/site-origin.mjs, covered by
src/tests/site-origin.test.ts.

scripts/enhance-seo-pages.mjs

@@ -3,15 +3,14 @@ import path from 'path';
 import { JSDOM } from 'jsdom';
 import { fileURLToPath } from 'url';
 import { serializeJsonLd } from './json-ld.mjs';
+import { DEFAULT_SITE_URL, rebaseDefaultOrigin } from './site-origin.mjs';
 
 const __filename = fileURLToPath(import.meta.url);
 const __dirname = path.dirname(__filename);
 
 const DIST_DIR = path.resolve(__dirname, '../dist');
-const SITE_URL = (process.env.SITE_URL || 'https://www.bentopdf.com').replace(
-  /\/+$/,
-  ''
-);
+const SITE_URL = (process.env.SITE_URL || DEFAULT_SITE_URL).replace(/\/+$/, '');
+const BLOG_DIST_DIR = path.join(DIST_DIR, 'blog');
 
 const FALLBACK_SOCIAL_IMAGE = '/images/og-tools.png';
 
@@ -22,6 +21,26 @@ function listTopLevelHtml() {
     .map((f) => path.join(DIST_DIR, f));
 }
 
+// generate-blog.mjs writes the blog index and posts with SITE_URL, but
+// hand-written blog pages (blog/author-alam.html) carry the official origin
+// literally, and generate-i18n-pages.mjs only rewrites top-level pages. Rebase
+// them here so a custom-SITE_URL build passes seo-audit's canonical check.
+function rebaseBlogPages() {
+  if (!fs.existsSync(BLOG_DIST_DIR)) return 0;
+  let rebased = 0;
+  for (const f of fs.readdirSync(BLOG_DIST_DIR)) {
+    if (!f.endsWith('.html')) continue;
+    const file = path.join(BLOG_DIST_DIR, f);
+    const html = fs.readFileSync(file, 'utf-8');
+    const out = rebaseDefaultOrigin(html, SITE_URL);
+    if (out !== html) {
+      fs.writeFileSync(file, out);
+      rebased++;
+    }
+  }
+  return rebased;
+}
+
 function imageExists(url) {
   if (!url) return true;
   let pathname;
@@ -159,8 +178,9 @@ function enhance() {
     fs.writeFileSync(file, dom.serialize());
     dom.window.close();
   }
+  const rebasedBlogPages = rebaseBlogPages();
   console.log(
-    `SEO enhance: ${files.length} pages processed, ${faqSchemaCount} FAQPage schemas added.`
+    `SEO enhance: ${files.length} pages processed, ${faqSchemaCount} FAQPage schemas added, ${rebasedBlogPages} blog pages rebased to ${SITE_URL}.`
   );
 }
 

scripts/generate-blog.mjs

@@ -3,13 +3,14 @@ import path from 'path';
 import { marked } from 'marked';
 import { fileURLToPath } from 'url';
 import { serializeJsonLd } from './json-ld.mjs';
+import { DEFAULT_SITE_URL } from './site-origin.mjs';
 
 const __filename = fileURLToPath(import.meta.url);
 const __dirname = path.dirname(__filename);
 
 const POSTS_DIR = path.resolve(__dirname, '../blog/posts');
 const BLOG_DIR = path.resolve(__dirname, '../blog');
-const SITE_URL = 'https://www.bentopdf.com';
+const SITE_URL = (process.env.SITE_URL || DEFAULT_SITE_URL).replace(/\/+$/, '');
 const AUTHOR = {
   name: 'Alam',
   url: `${SITE_URL}/blog/author-alam`,

scripts/site-origin.mjs

@@ -0,0 +1,19 @@
+/**
+ * The public origin the build writes into canonical / og:url / JSON-LD URLs.
+ * Self-hosters set SITE_URL at build time; the default is the official site.
+ */
+export const DEFAULT_SITE_URL = 'https://www.bentopdf.com';
+
+const DEFAULT_ORIGIN_RE = /https:\/\/www\.bentopdf\.com(?![\w.-])/g;
+
+/**
+ * Rewrites absolute URLs on the default origin to `siteUrl` (no trailing
+ * slash). Used for hand-written pages that carry the official origin
+ * literally, so a build with a custom SITE_URL emits canonicals on its own
+ * host. Other hosts, including look-alikes such as
+ * `https://www.bentopdf.com.example`, are left untouched.
+ */
+export function rebaseDefaultOrigin(html, siteUrl) {
+  if (siteUrl === DEFAULT_SITE_URL) return html;
+  return html.replace(DEFAULT_ORIGIN_RE, siteUrl);
+}

src/tests/site-origin.test.ts

@@ -0,0 +1,41 @@
+import { describe, it, expect } from 'vitest';
+import {
+  DEFAULT_SITE_URL,
+  rebaseDefaultOrigin,
+} from '../../scripts/site-origin.mjs';
+
+const PAGE = `<link rel="canonical" href="https://www.bentopdf.com/blog/author-alam" />
+<meta property="og:image" content="https://www.bentopdf.com/images/author-alam.jpg" />
+<script type="application/ld+json">{"url":"https://www.bentopdf.com","sameAs":["https://github.com/alam00000"]}</script>`;
+
+describe('rebaseDefaultOrigin', () => {
+  it('rewrites every default-origin URL to the custom site URL', () => {
+    const out = rebaseDefaultOrigin(PAGE, 'https://pdf.example.org');
+    expect(out).not.toContain('www.bentopdf.com');
+    expect(out).toContain('href="https://pdf.example.org/blog/author-alam"');
+    expect(out).toContain(
+      'content="https://pdf.example.org/images/author-alam.jpg"'
+    );
+    expect(out).toContain('"url":"https://pdf.example.org"');
+    expect(out).toContain('https://github.com/alam00000');
+  });
+
+  it('keeps a subpath site URL intact', () => {
+    expect(
+      rebaseDefaultOrigin(
+        'href="https://www.bentopdf.com/blog/"',
+        'https://example.org/pdf'
+      )
+    ).toBe('href="https://example.org/pdf/blog/"');
+  });
+
+  it('leaves look-alike hosts alone', () => {
+    const html =
+      'href="https://www.bentopdf.com.example/x" href="https://www.bentopdf.community/"';
+    expect(rebaseDefaultOrigin(html, 'https://pdf.example.org')).toBe(html);
+  });
+
+  it('is a no-op for the default site URL', () => {
+    expect(rebaseDefaultOrigin(PAGE, DEFAULT_SITE_URL)).toBe(PAGE);
+  });
+});