chore: add sitemap generator

web/package.json

@@ -5,7 +5,7 @@
 	"type": "module",
 	"scripts": {
 		"dev": "vite dev",
-		"build": "vite build",
+		"build": "vite build && node scripts/gen-sitemap.mjs",
 		"preview": "vite preview",
 		"prepare": "svelte-kit sync || echo ''",
 		"check": "svelte-kit sync && svelte-check --tsconfig ./tsconfig.json",

web/scripts/gen-sitemap.mjs

@@ -0,0 +1,96 @@
+// Writes build/sitemap.xml right after `vite build` (adapter-static already
+// emitted the HTML there). The URL set is read back from the build output
+// instead of the registry: prerendered pages are exactly the pages that exist,
+// and a page whose HTML carries `noindex` is skipped, so the sitemap can never
+// drift from what was shipped or advertise a page we ask crawlers to ignore.
+import { existsSync, readFileSync, readdirSync, writeFileSync } from "node:fs";
+import { join, relative, sep } from "node:path";
+import { fileURLToPath } from "node:url";
+
+const BUILD_DIR = fileURLToPath(new URL("../build/", import.meta.url));
+
+function siteOrigin() {
+	const fromEnv = (process.env.PUBLIC_SITE_ORIGIN ?? "").trim();
+	if (fromEnv !== "") return fromEnv.replace(/\/+$/, "");
+
+	// Local builds run without CI env vars; `static/CNAME` is the domain GitHub
+	// Pages publishes under, so it is the same truth as the deploy-time env.
+	const cnamePath = fileURLToPath(new URL("../static/CNAME", import.meta.url));
+	if (!existsSync(cnamePath)) {
+		throw new Error(
+			"gen-sitemap: no site origin — set PUBLIC_SITE_ORIGIN or add web/static/CNAME",
+		);
+	}
+	const cname = readFileSync(cnamePath, "utf8").trim();
+	if (cname === "") {
+		throw new Error("gen-sitemap: web/static/CNAME is empty");
+	}
+	return `https://${cname}`;
+}
+
+/** Mirrors the `base` normalization in vite.config.ts. */
+const rawBase = (process.env.BASE_PATH ?? "").trim();
+const base =
+	rawBase === "" || rawBase === "/"
+		? ""
+		: `/${rawBase.replace(/^\/+/, "").replace(/\/+$/, "")}`;
+
+function* htmlFiles(dir) {
+	for (const entry of readdirSync(dir, { withFileTypes: true })) {
+		const full = join(dir, entry.name);
+		if (entry.isDirectory()) yield* htmlFiles(full);
+		else if (entry.name.endsWith(".html")) yield full;
+	}
+}
+
+/**
+ * adapter-static names prerendered pages `<route>.html` (`tools/crop-png.html`)
+ * because `trailingSlash` is "never"; the `index.html` form covers a future
+ * switch. GitHub Pages serves the flat file at the extension-less URL.
+ */
+function routePath(file) {
+	const rel = relative(BUILD_DIR, file).split(sep).join("/");
+	if (rel === "404.html") return null;
+	if (rel === "index.html") return "/";
+	if (rel.endsWith("/index.html"))
+		return `/${rel.slice(0, -"index.html".length)}`;
+	return `/${rel.slice(0, -".html".length)}`;
+}
+
+function escapeXml(value) {
+	return value.replace(/&/g, "&amp;").replace(/</g, "&lt;");
+}
+
+if (!existsSync(BUILD_DIR)) {
+	throw new Error("gen-sitemap: build/ is missing — run `vite build` first");
+}
+
+const origin = siteOrigin();
+const locs = [];
+
+for (const file of htmlFiles(BUILD_DIR)) {
+	const html = readFileSync(file, "utf8");
+	if (/<meta\s+name="robots"\s+content="[^"]*noindex/.test(html)) continue;
+
+	const route = routePath(file);
+	if (route === null) continue;
+
+	locs.push(`${origin}${base}${route}`);
+}
+
+if (locs.length === 0) {
+	throw new Error("gen-sitemap: no indexable pages found in build/");
+}
+
+locs.sort();
+
+const xml = [
+	'<?xml version="1.0" encoding="UTF-8"?>',
+	'<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">',
+	...locs.map((loc) => `\t<url><loc>${escapeXml(loc)}</loc></url>`),
+	"</urlset>",
+	"",
+].join("\n");
+
+writeFileSync(join(BUILD_DIR, "sitemap.xml"), xml);
+console.log(`sitemap.xml written: ${locs.length} urls (origin ${origin})`);

web/src/routes/kit/+page.svelte

@@ -41,6 +41,10 @@
 	);
 </script>
 
+<svelte:head>
+	<meta name="robots" content="noindex, nofollow" />
+</svelte:head>
+
 <div class="showcase">
 	<header class="showcase-head">
 		<span class="showcase-eyebrow">KIT SHOWCASE</span>

web/static/robots.txt

@@ -1,3 +1,9 @@
 # allow crawling everything by default
 User-agent: *
 Disallow:
+
+# Service pages (/kit) are excluded from the index with a `noindex` meta tag,
+# not with Disallow: a blocked-but-not-noindexed URL shows up in Search Console
+# as an error and keeps its old indexed snippet.
+
+Sitemap: https://easy-image-tools.com/sitemap.xml