Add sitemap generation utility

2026-10-14 17:41:50 +01:00
parent d9de858439
commit 632881e174
9 changed files with 289 additions and 1 deletions
@@ -0,0 +1,165 @@
+import { statSync } from "fs";
+import path from "path";
+import grabPageServerPath from "../functions/server/web-pages/grab-page-server-path";
+import grabAllPages from "./grab-all-pages";
+import grabDirNames from "./grab-dir-names";
+import grabOrigin from "./grab-origin";
+import grabRelativePath from "./grab-relative-path";
+import isDevelopment from "./is-development";
+const ErrorPagePaths = ["/404", "/500"];
+/**
+ * # Generate a sitemap.xml string for all pages
+ * Dynamic routes are only included through a `sitemap` export in their
+ * `.server.ts` file, or through `additional_paths`.
+ */
+export default async function generateSitemap(params) {
+    const entries = await grabSitemapEntries(params);
+    const origin = (params?.origin || grabOrigin()).replace(/\/+$/, "");
+    const urls = entries.map((entry) => {
+        const loc = entry.path.match(/^https?:\/\//)
+            ? entry.path
+            : `${origin}${entry.path}`;
+        const lines = [`        <loc>${escapeXml(loc)}</loc>`];
+        if (entry.lastmod) {
+            const lastmod = entry.lastmod instanceof Date
+                ? entry.lastmod.toISOString()
+                : entry.lastmod;
+            lines.push(`        <lastmod>${escapeXml(lastmod)}</lastmod>`);
+        }
+        if (entry.changefreq) {
+            lines.push(`        <changefreq>${entry.changefreq}</changefreq>`);
+        }
+        if (typeof entry.priority == "number") {
+            const priority = Math.min(Math.max(entry.priority, 0), 1);
+            lines.push(`        <priority>${priority.toFixed(1)}</priority>`);
+        }
+        return `    <url>\n${lines.join("\n")}\n    </url>`;
+    });
+    return [
+        `<?xml version="1.0" encoding="UTF-8"?>`,
+        `<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">`,
+        ...urls,
+        `</urlset>`,
+        ``,
+    ].join("\n");
+}
+export async function grabSitemapEntries(params) {
+    const use_file_lastmod = params?.use_file_lastmod ?? true;
+    const entries = [];
+    const pages = grabAllPages({ exclude_api: true });
+    for (let i = 0; i < pages.length; i++) {
+        const page = pages[i];
+        if (!page.local_path)
+            continue;
+        const page_path = page.url_path.replace(/\/index$/, "") || "/";
+        if (ErrorPagePaths.includes(page_path))
+            continue;
+        const page_sitemap_paths = await grabPageSitemapPaths({
+            file_path: page.local_path,
+            route: page_path,
+        });
+        if (page_sitemap_paths) {
+            entries.push(...page_sitemap_paths.map(toSitemapEntry));
+            continue;
+        }
+        if (page.url_path.match(/\[/))
+            continue;
+        entries.push({
+            path: page_path,
+            lastmod: use_file_lastmod
+                ? statSync(page.local_path).mtime
+                : undefined,
+        });
+    }
+    const additional_paths = typeof params?.additional_paths == "function"
+        ? await params.additional_paths()
+        : params?.additional_paths;
+    entries.push(...(additional_paths || []).map(toSitemapEntry));
+    const seen = new Set();
+    const final_entries = [];
+    for (const entry of entries) {
+        const path = normalizePath(entry.path, params?.trailing_slash);
+        if (seen.has(path))
+            continue;
+        if (isExcluded(path, params?.exclude))
+            continue;
+        seen.add(path);
+        final_entries.push({
+            changefreq: params?.default_changefreq,
+            priority: params?.default_priority,
+            ...entry,
+            path,
+        });
+    }
+    return final_entries;
+}
+/**
+ * # Run the `sitemap` export of a page's server file, if any
+ */
+async function grabPageSitemapPaths({ file_path, route, }) {
+    const { server_file_path } = grabPageServerPath({ file_path });
+    if (!server_file_path)
+        return;
+    const { ROOT_DIR } = grabDirNames();
+    const server_ctx = global.BUNEXT_SSR_BUNDLER_CTX_MAP?.[grabRelativePath(server_file_path)];
+    const final_server_path = server_ctx?.local_path
+        ? path.join(ROOT_DIR, server_ctx.path)
+        : server_file_path;
+    // Bust the import cache in development so edits to the server file
+    // are picked up without a restart.
+    const server_module = await import(isDevelopment()
+        ? `${final_server_path}?t=${Date.now()}`
+        : final_server_path);
+    if (typeof server_module.sitemap != "function")
+        return;
+    try {
+        return await server_module.sitemap({ route });
+    }
+    catch (error) {
+        throw new Error(`\`sitemap\` export of ${grabRelativePath(server_file_path)} failed: ${error?.message || error}`);
+    }
+}
+function toSitemapEntry(path) {
+    return typeof path == "string" ? { path } : path;
+}
+function normalizePath(path, trailing_slash) {
+    if (path.match(/^https?:\/\//))
+        return path;
+    let new_path = `/${path}`.replace(/\/{2,}/g, "/");
+    if (new_path != "/")
+        new_path = new_path.replace(/\/$/, "");
+    if (trailing_slash && new_path != "/")
+        new_path += "/";
+    return new_path;
+}
+function isExcluded(path, exclude) {
+    if (!exclude?.length)
+        return false;
+    const bare_path = path.replace(/^https?:\/\/[^/]+/, "").replace(/(.)\/$/, "$1") || "/";
+    for (const pattern of exclude) {
+        if (pattern instanceof RegExp) {
+            if (pattern.test(path) || pattern.test(bare_path))
+                return true;
+            continue;
+        }
+        const normalized = normalizePath(pattern.replace(/\/\*$/, ""));
+        if (pattern.endsWith("/*")) {
+            if (bare_path == normalized ||
+                bare_path.startsWith(`${normalized.replace(/\/$/, "")}/`)) {
+                return true;
+            }
+        }
+        else if (bare_path == normalized) {
+            return true;
+        }
+    }
+    return false;
+}
+function escapeXml(value) {
+    return value
+        .replace(/&/g, "&amp;")
+        .replace(/</g, "&lt;")
+        .replace(/>/g, "&gt;")
+        .replace(/"/g, "&quot;")
+        .replace(/'/g, "&apos;");
+}