docs(readme): add Roman Urdu edition (#6499)

* docs(readme): add Roman Urdu edition

Register ur-Latn with a pending website catalog and preserve English command examples.

Script-tag handling follows morluto's shared helper proposed in PR #2043 (c46f606c89).

* test(website): cover completed script-tag page metadata

scripts/test-website.py

@@ -541,6 +541,72 @@ class WebsiteMaintenanceChecks(unittest.TestCase):
 class WebsiteTranslationChecks(unittest.TestCase):
     """Exercise source edits, translated evidence and language editions at their consumers."""
 
+    def test_language_inventory_preserves_script_identity(self):
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            (root / "website/locales").mkdir(parents=True)
+            for code in ("ur", "ur-PK", "ur-Latn", "ur-Latn-PK", "hi-Latn"):
+                inventory = [
+                    {"code": "en", "name": "English", "readme": "README.md", "dir": "ltr"},
+                    {"code": code, "name": "Fixture", "readme": f"docs/readme/README_{code}.md", "dir": "ltr"},
+                ]
+                path = root / "website/locales/languages.json"
+                path.write_text(json.dumps(inventory))
+                with self.subTest(code=code):
+                    self.assertEqual(languages(root), inventory)
+            for code in ("ur-latn", "ur-LATN", "ur-PK-Latn", "ur/Latn"):
+                inventory[1]["code"] = code
+                path.write_text(json.dumps(inventory))
+                with self.subTest(code=code), self.assertRaisesRegex(ValueError, "Invalid or duplicate language"):
+                    languages(root)
+
+    def test_completed_script_tag_pages_pass_search_metadata(self):
+        with tempfile.TemporaryDirectory() as directory:
+            site = Path(directory)
+            (site / "assets").mkdir()
+            shutil.copyfile(ROOT / "website/_site/assets/social-card.png", site / "assets/social-card.png")
+            shutil.copyfile(ROOT / "website/public/robots.txt", site / "robots.txt")
+            pages = {}
+            for code in ("ur-Latn", "ur-Latn-PK"):
+                path = site / code / "index.html"
+                path.parent.mkdir()
+                url = f"https://rea.tools/{code}/"
+                source = dedent(f'''\
+                    <!doctype html>
+                    <html lang="{code}" dir="ltr">
+                    <head>
+                      <title>REA ka ta'aruf</title>
+                      <meta name="description" content="REA ko samjhein." />
+                      <link rel="canonical" href="{url}" />
+                      <link rel="alternate" hreflang="{code}" href="{url}" />
+                      <meta property="og:type" content="website" />
+                      <meta property="og:site_name" content="REA" />
+                      <meta property="og:title" content="REA ka ta'aruf" />
+                      <meta property="og:description" content="REA ko samjhein." />
+                      <meta property="og:url" content="{url}" />
+                      <meta property="og:image" content="https://rea.tools/assets/social-card.png" />
+                      <meta property="og:image:type" content="image/png" />
+                      <meta property="og:image:width" content="1200" />
+                      <meta property="og:image:height" content="630" />
+                      <meta property="og:image:alt" content="REA" />
+                      <meta name="twitter:card" content="summary_large_image" />
+                      <meta name="twitter:title" content="REA ka ta'aruf" />
+                      <meta name="twitter:description" content="REA ko samjhein." />
+                      <meta name="twitter:image" content="https://rea.tools/assets/social-card.png" />
+                      <meta name="twitter:image:alt" content="REA" />
+                    </head>
+                    <body><h1>REA ka ta'aruf</h1></body>
+                    </html>
+                ''')
+                path.write_text(source, encoding="utf-8")
+                page = VERIFY.HtmlReferences()
+                page.feed(source)
+                self.assertFalse(page.translation_fallback)
+                self.assertFalse(page.noindex())
+                pages[path] = page
+            PREPARE.prepare_sitemap(site)
+            self.assertEqual(VERIFY.check_search_metadata(site, pages), (2, []))
+
     @contextlib.contextmanager
     def translated_project(self):
         with tempfile.TemporaryDirectory() as directory:

scripts/verify-website.py

@@ -11,6 +11,7 @@ import xml.etree.ElementTree as ET
 from zipfile import BadZipFile, ZipFile
 
 from website import NOTES_FIXTURES, SITE_ORIGIN, authored_markdown, page_url, sync_pages
+from website_i18n import is_language_code
 
 LEGACY_ORIGIN = "morluto.github.io"
 SITE_TEXT_URL = re.compile(
@@ -179,7 +180,7 @@ def check_search_metadata(site, pages):
         if not title:
             errors.append(f"{label}: needs exactly one nonempty head title")
         first = path.relative_to(site).parts[0]
-        expected_language = first if re.fullmatch(r"[a-z]{2}(?:-[A-Z]{2})?", first) else "en"
+        expected_language = first if is_language_code(first) else "en"
         if page.translation_fallback:
             if page.lang != "en" or not page.noindex():
                 errors.append(f"{label}: English translation fallback needs lang=en and noindex")

scripts/website_i18n.py

@@ -25,6 +25,14 @@ LITERALS = {"REA", "Reverse Engineer Anything", "REA · Reverse Engineer Anythin
 FALLBACK_NOTICE = "Translation is being updated. Read this page in English for now."
 
 
+LANGUAGE_CODE = re.compile(r"[a-z]{2}(?:-[A-Z][a-z]{3})?(?:-[A-Z]{2})?")
+
+
+def is_language_code(value):
+    """Recognize canonical language, optional script and region inventory codes."""
+    return LANGUAGE_CODE.fullmatch(value) is not None
+
+
 def readme_edition_paths(root):
     """Return repo-relative README editions: root English plus docs/readme translations."""
     editions = set()
@@ -57,7 +65,7 @@ def languages(root):
             raise ValueError("Each language needs code, name, readme and dir")
         if not all(isinstance(value, str) and value for value in item.values()):
             raise ValueError("Language fields must be nonempty strings")
-        if not re.fullmatch(r"[a-z]{2}(?:-[A-Z]{2})?", item["code"]) or item["code"] in codes:
+        if not is_language_code(item["code"]) or item["code"] in codes:
             raise ValueError(f"Invalid or duplicate language: {item['code']}")
         if item["dir"] not in ("ltr", "rtl"):
             raise ValueError(f"Invalid text direction: {item['code']}")