feat(sitemap): add namespaces configuration option (#14285)

Co-authored-by: Sarah Rainsberger <[email protected]>
Co-authored-by: Florian Lefebvre <[email protected]>

Author: 3 people

.changeset/rich-insects-scream.md

@@ -0,0 +1,41 @@
+---
+'@astrojs/sitemap': minor
+---
+
+Adds a new configuration option `namespaces` for more control over XML namespaces used in sitemap generation
+
+Excluding unused namespaces can help create cleaner, more focused sitemaps that are faster for search engines to parse and use less bandwidth. If your site doesn't have news content, videos, or multiple languages, you can exclude those namespaces to reduce XML bloat.
+
+The `namespaces` option allows you to configure `news`, `xhtml`, `image`, and `video` namespaces independently. All namespaces are enabled by default for backward compatibility and no change to existing projects is necessary. But now, you can choose to streamline your XML and avoid unnecessary code.
+
+For example, to exclude the video namespace from your sitemap, set `video: false` in your configuration:
+
+```
+// astro.config.mjs
+import { sitemap } from '@astrojs/sitemap';
+
+export default {
+  integrations: [
+    sitemap({
+      namespaces: {
+        video: false,
+        // other namespaces remain enabled by default
+      }
+    })
+  ]
+};
+```
+
+The generated XML will not include the `xmlns:video` namespace:
+
+```
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset
+  xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+  xmlns:news="http://www.google.com/schemas/sitemap-news/0.9"
+  xmlns:xhtml="http://www.w3.org/1999/xhtml"
+  xmlns:image="http://www.google.com/schemas/sitemap-image/1.1"
+>
+  <!-- ... -->
+</urlset>
+```

packages/integrations/sitemap/src/config-defaults.ts

@@ -3,4 +3,10 @@ import type { SitemapOptions } from './index.js';
 export const SITEMAP_CONFIG_DEFAULTS = {
 	filenameBase: 'sitemap',
 	entryLimit: 45000,
+	namespaces: {
+		news: true,
+		xhtml: true, 
+		image: true,
+		video: true,
+	},
 } satisfies SitemapOptions;

packages/integrations/sitemap/src/index.ts

@@ -39,6 +39,14 @@ export type SitemapOptions =
 			serialize?(item: SitemapItem): SitemapItem | Promise<SitemapItem | undefined> | undefined;
 
 			xslURL?: string;
+			
+		// namespace configuration
+			namespaces?: {
+				news?: boolean;
+				xhtml?: boolean;
+				image?: boolean;
+				video?: boolean;
+			};
 	  }
 	| undefined;
 
@@ -180,6 +188,7 @@ const createPlugin = (options?: SitemapOptions): AstroIntegration => {
 							customSitemaps,
 							xslURL: xslURL,
 							lastmod,
+							namespaces: opts.namespaces,
 						},
 						config,
 					);

packages/integrations/sitemap/src/schema.ts

@@ -37,6 +37,16 @@ export const SitemapOptionsSchema = z
 		changefreq: z.nativeEnum(ChangeFreq).optional(),
 		lastmod: z.date().optional(),
 		priority: z.number().min(0).max(1).optional(),
+
+		namespaces: z
+			.object({
+					news: z.boolean().optional(),
+					xhtml: z.boolean().optional(),
+					image: z.boolean().optional(),
+					video: z.boolean().optional(),
+			})
+			.optional()
+			.default(SITEMAP_CONFIG_DEFAULTS.namespaces),
 	})
 	.strict()
 	.default(SITEMAP_CONFIG_DEFAULTS);

packages/integrations/sitemap/src/write-sitemap.ts

@@ -19,6 +19,12 @@ type WriteSitemapConfig = {
 	limit?: number;
 	xslURL?: string;
 	lastmod?: string;
+	namespaces?: {
+		news?: boolean;
+		xhtml?: boolean;
+		image?: boolean;
+		video?: boolean;
+	};
 };
 
 // adapted from sitemap.js/sitemap-simple
@@ -34,6 +40,7 @@ export async function writeSitemap(
 		publicBasePath = './',
 		xslURL: xslUrl,
 		lastmod,
+		namespaces = { news: true, xhtml: true, image: true, video: true },
 	}: WriteSitemapConfig,
 	astroConfig: AstroConfig,
 ) {
@@ -46,6 +53,13 @@ export async function writeSitemap(
 			const sitemapStream = new SitemapStream({
 				hostname,
 				xslUrl,
+				// Custom namespace handling
+				xmlns: {
+					news: namespaces?.news !== false,
+					xhtml: namespaces?.xhtml !== false,
+					image: namespaces?.image !== false,
+					video: namespaces?.video !== false,
+				},
 			});
 			const path = `./${filenameBase}-${i}.xml`;
 			const writePath = resolve(destinationDir, path);

packages/integrations/sitemap/test/namespaces.test.js

@@ -0,0 +1,79 @@
+import assert from 'node:assert/strict';
+import { before, describe, it } from 'node:test';
+import { sitemap } from './fixtures/static/deps.mjs';
+import { loadFixture } from './test-utils.js';
+
+describe('Namespaces Configuration', () => {
+    let fixture;
+
+    describe('Default namespaces', () => {
+        before(async () => {
+            fixture = await loadFixture({
+                root: './fixtures/static/',
+                integrations: [sitemap()],
+            });
+            await fixture.build();
+        });
+
+        it('includes all default namespaces', async () => {
+            const xml = await fixture.readFile('/sitemap-0.xml');
+            assert.ok(xml.includes('xmlns:news="http://www.google.com/schemas/sitemap-news/0.9"'));
+            assert.ok(xml.includes('xmlns:xhtml="http://www.w3.org/1999/xhtml"'));
+            assert.ok(xml.includes('xmlns:image="http://www.google.com/schemas/sitemap-image/1.1"'));
+            assert.ok(xml.includes('xmlns:video="http://www.google.com/schemas/sitemap-video/1.1"'));
+        });
+    });
+
+    describe('Excluding news namespace', () => {
+        before(async () => {
+            fixture = await loadFixture({
+                root: './fixtures/static/',
+                integrations: [
+                    sitemap({
+                        namespaces: {
+                            news: false,
+                        },
+                    }),
+                ],
+            });
+            await fixture.build();
+        });
+
+        it('excludes news namespace but includes others', async () => {
+            const xml = await fixture.readFile('/sitemap-0.xml');
+            assert.ok(!xml.includes('xmlns:news="http://www.google.com/schemas/sitemap-news/0.9"'));
+            assert.ok(xml.includes('xmlns:xhtml="http://www.w3.org/1999/xhtml"'));
+            assert.ok(xml.includes('xmlns:image="http://www.google.com/schemas/sitemap-image/1.1"'));
+            assert.ok(xml.includes('xmlns:video="http://www.google.com/schemas/sitemap-video/1.1"'));
+        });
+    });
+
+    describe('Minimal namespaces', () => {
+        before(async () => {
+            fixture = await loadFixture({
+                root: './fixtures/static/',
+                integrations: [
+                    sitemap({
+                        namespaces: {
+                            news: false,
+                            xhtml: false,
+                            image: false,
+                            video: false,
+                        },
+                    }),
+                ],
+            });
+            await fixture.build();
+        });
+
+        it('excludes all optional namespaces', async () => {
+            const xml = await fixture.readFile('/sitemap-0.xml');
+            assert.ok(!xml.includes('xmlns:news="http://www.google.com/schemas/sitemap-news/0.9"'));
+            assert.ok(!xml.includes('xmlns:xhtml="http://www.w3.org/1999/xhtml"'));
+            assert.ok(!xml.includes('xmlns:image="http://www.google.com/schemas/sitemap-image/1.1"'));
+            assert.ok(!xml.includes('xmlns:video="http://www.google.com/schemas/sitemap-video/1.1"'));
+            // Still includes the main sitemap namespace
+            assert.ok(xml.includes('xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"'));
+        });
+    });
+});