fix(content-blog): links in feed should be absolute

packages/docusaurus-plugin-content-blog/src/__tests__/feed.test.ts

@@ -8,12 +8,18 @@
 import {jest} from '@jest/globals';
 import path from 'path';
 import fs from 'fs-extra';
+import {load as cheerioLoad} from 'cheerio';
+import {readOutputHTMLFile} from '@docusaurus/utils';
+import {blogPostContainerID} from '@docusaurus/utils-common';
 import {DEFAULT_OPTIONS} from '../options';
 import {generateBlogPosts} from '../blogUtils';
-import {createBlogFeedFiles} from '../feed';
-import type {LoadContext, I18n} from '@docusaurus/types';
+import {
+  createBlogFeedFiles,
+  defaultCreateFeedItems as feedDefaultCreateFeedItems,
+} from '../feed';
+import type {LoadContext, I18n, DocusaurusConfig} from '@docusaurus/types';
 import type {BlogContentPaths} from '../types';
-import type {PluginOptions} from '@docusaurus/plugin-content-blog';
+import type {BlogPost, PluginOptions} from '@docusaurus/plugin-content-blog';
 
 const DefaultI18N: I18n = {
   currentLocale: 'en',
@@ -62,6 +68,32 @@
   });
 }
 
+function isFullAbsolutePath(str: string) {
+  const domain = 'https://domain.com';
+  const {origin} = new URL(str, domain);
+  return origin !== domain;
+}
+
+async function generateLinksOfBlogPosts(outDir: string, blogPosts: BlogPost[]) {
+  const linksOfBlogPosts: {[postId: string]: string[]} = {};
+  const pathOfFile = path.join(outDir, 'blog');
+  const promises = blogPosts.map(async (post) => {
+    try {
+      const content = await readOutputHTMLFile(post.id, pathOfFile, true);
+      const $ = cheerioLoad(content);
+      const anchorElements = $(`div#${blogPostContainerID} a`);
+      if (anchorElements.length > 0) {
+        const href = anchorElements.map((_, elm) => elm.attribs.href).toArray();
+        linksOfBlogPosts[post.id] = href;
+      }
+    } catch {
+      // post is a draft
+    }
+  });
+  await Promise.all(promises);
+  return linksOfBlogPosts;
+}
+
 describe.each(['atom', 'rss', 'json'])('%s', (feedType) => {
   const fsMock = jest.spyOn(fs, 'outputFile').mockImplementation(() => {});
 
@@ -140,7 +172,7 @@
 
     expect(
       fsMock.mock.calls.map((call) => call[1] as string),
     ).toMatchSnapshot();
     fsMock.mockClear();
   });
 
@@ -192,7 +224,99 @@
 
     expect(
       fsMock.mock.calls.map((call) => call[1] as string),
     ).toMatchSnapshot();
     fsMock.mockClear();
   });
 });
+
+describe('Test defaultCreateFeedItems', () => {
+  const fsMock = jest.spyOn(fs, 'outputFile').mockImplementation(() => {});
+  it('links in feeds are resolved correctly', async () => {
+    const siteDir = path.join(__dirname, '__fixtures__', 'website');
+    const outDir = path.join(siteDir, 'build-snap');
+    const siteConfig = {
+      title: 'Hello',
+      baseUrl: '/myBaseUrl/',
+      url: 'https://docusaurus.io',
+      favicon: 'image/favicon.ico',
+    } as DocusaurusConfig;
+
+    const context = {
+      siteDir,
+      siteConfig,
+      i18n: DefaultI18N,
+      outDir,
+    } as LoadContext;
+
+    const options = {
+      path: 'blog',
+      routeBasePath: 'blog',
+      tagsBasePath: 'tags',
+      authorsMapPath: 'authors.yml',
+      include: DEFAULT_OPTIONS.include,
+      exclude: DEFAULT_OPTIONS.exclude,
+      feedOptions: {
+        type: ['atom', 'rss', 'json'],
+        copyright: 'Copyright',
+      },
+      readingTime: ({content, defaultReadingTime}) =>
+        defaultReadingTime({content}),
+      truncateMarker: /<!--\s*truncate\s*-->/,
+    } as PluginOptions;
+
+    const blogPosts = await generateBlogPosts(
+      getBlogContentPaths(siteDir),
+      context,
+      options,
+    );
+
+    await createBlogFeedFiles({
+      blogPosts,
+      options,
+      siteConfig: context.siteConfig,
+      outDir: context.outDir,
+      locale: 'en',
+    });
+
+    const originalLinksInBlogs: {[id: string]: Array<string>} =
+      await generateLinksOfBlogPosts(outDir, blogPosts);
+
+    const blogPostsWithLinks = blogPosts.filter(
+      (post) => originalLinksInBlogs[post.id],
+    );
+
+    const feedsWithLinks = await feedDefaultCreateFeedItems({
+      blogPosts: blogPostsWithLinks,
+      siteConfig,
+      outDir,
+    });
+
+    feedsWithLinks.forEach((feed) => {
+      const $ = cheerioLoad(feed.content ?? '');
+      const linksInFeed = $('a')
+        .map((_, elm) => elm.attribs.href)
+        .toArray();
+      const idOfBlogPost = feed.id!.replace(
+        new URL(`${siteConfig.baseUrl}blog`, siteConfig.url).href,
+        '',
+      );
+      const originalLinksInBlog = originalLinksInBlogs[idOfBlogPost];
+      const {permalink = ''} =
+        blogPostsWithLinks.find((post) => post.id === idOfBlogPost)?.metadata ||
+        {};
+
+      originalLinksInBlog!.forEach((originalLinkInBlog, idx) => {
+        const linkToTest = isFullAbsolutePath(originalLinkInBlog)
+          ? originalLinkInBlog
+          : new URL(originalLinkInBlog, new URL(permalink, siteConfig.url))
+              .href;
+
+        expect(linkToTest).toEqual(linksInFeed[idx]);
+      });
+    });
+    expect(
+      fsMock.mock.calls.map((call) => call[1] as string),
+    ).toMatchSnapshot();
+    fsMock.mockClear();
+  });
+});

packages/docusaurus-plugin-content-blog/src/feed.ts

@@ -70,7 +70,7 @@ async function generateBlogFeed({
   return feed;
 }
 
-async function defaultCreateFeedItems({
+export async function defaultCreateFeedItems({
   blogPosts,
   siteConfig,
   outDir,
@@ -106,6 +106,14 @@ async function defaultCreateFeedItems({
       const $ = cheerioLoad(content);
 
       const link = normalizeUrl([siteUrl, permalink]);
+
+      $(`div#${blogPostContainerID} a`).each((_, elm) => {
+        const {href} = elm.attribs;
+        if (href) {
+          elm.attribs.href = String(new URL(href, link));
+        }
+      });
+
       const feedItem: BlogFeedItem = {
         title: metadataTitle,
         id: link,

website/_dogfooding/_blog tests/2023-07-19-a.mdx

@@ -0,0 +1,9 @@
+---
+title: 'Test if href in feed resolved correctly'
+---
+
+[absolute full url](https://github.com/facebook/docusaurus)
+
+[absolute url with implicit domain name](/tests/blog/2023/07/19/b)
+
+[relative url](2023-07-19-b.mdx)

website/_dogfooding/_blog tests/2023-07-19-b.mdx

@@ -0,0 +1 @@
+# Test Relative Path