v4: link previews are read once, in one place, and no longer take an error page, a relative image or a mask icon for the page's — each provider fetched its page and scanned it with regular expressions of its own, the generic one some fifteen times, and Bandcamp and SoundCloud read only OG tags. fetchPage (remote/fetch.ts) now fetches every page, follows redirects to the address it was served from, and refuses an error status, so a 404 or a bot challenge is unreachable rather than a preview titled "Just a moment...", and a refresh no longer overwrites good metadata with it. parsePage (remote/html.ts) reads it in one linear pass with a real attribute reader: unquoted values, a > inside quotes, og: tags under name as well as property, and nothing from comments or scripts. Every URL a page names is resolved against where it was served from, so a relative og:image works; entities are decoded in one pass, &eacute; and &rsquo; included, and one that names no character no longer fails the preview (bandcamp-tralbum.ts shares the decoder). The mask icon is no longer the favicon, JSON-LD prefers the page's node over the site's, tracking pixels and lazy placeholders aren't thumbnails, an og:url with a slug keeps the OG tags, and a <title> loses its site suffix. genericPreview is the base of the Bandcamp, SoundCloud and YouTube channel previews; SoundCloud takes www., m. and on.soundcloud.com short links, embedding the page they lead to, and Bandcamp keeps only its own player. The service tidies every preview: text on one line, titles and descriptions capped, only http(s) images and players. RichContent.type is now RichContentType, and the unused videoId is gone.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
khannurien
2026-10-09 20:46:32 +00:00
parent b4936cccf7
commit 2c3ba6ad11
22 changed files with 1111 additions and 519 deletions

View File

@@ -21,7 +21,7 @@ describe("JournalCard", () => {
<JournalCard
dump={makeDump({
richContent: {
type: "link",
type: "generic",
url: "u",
thumbnailUrl: "https://i.test/a.png",
},

View File

@@ -3,6 +3,7 @@ import { screen } from "@testing-library/react";
import { userEvent } from "@testing-library/user-event";
import { RichContentCard } from "../../../components/dump/RichContentCard.tsx";
import { renderWithContexts } from "../../render.tsx";
import type { RichContent } from "../../../../shared/dump.ts";
describe("RichContentCard", () => {
const yt = {
@@ -13,7 +14,7 @@ describe("RichContentCard", () => {
description: "About it",
thumbnailUrl: "https://i.ytimg.com/x.jpg",
embedUrl: "https://www.youtube.com/embed/x",
};
} satisfies RichContent;
test("full card: play button, source link and details", async () => {
const play = vi.fn();
@@ -52,7 +53,7 @@ describe("RichContentCard", () => {
renderWithContexts(
<RichContentCard
richContent={{
type: "link",
type: "generic",
url: "https://blog.test/p",
siteName: "Blog",
}}
@@ -85,7 +86,7 @@ describe("RichContentCard", () => {
type: "bandcamp",
url: "https://a.bandcamp.com/album/x",
embedUrl: "https://bandcamp.com/EmbeddedPlayer/1",
};
} satisfies RichContent;
renderWithContexts(<RichContentCard richContent={bc} compact />, {
player: {
togglePlay,

View File

@@ -337,7 +337,7 @@ describe("DumpEdit page", () => {
comment: "old why",
categoryIds: [],
richContent: {
type: "link",
type: "generic",
url: "https://a.test/",
title: "Page's own title",
},
@@ -452,7 +452,7 @@ describe("DumpEdit page", () => {
wire({
...urlDump(),
richContent: {
type: "link",
type: "generic",
url: "https://a.test/",
title: "Fresh title",
description: "New blurb",

View File

@@ -45,7 +45,7 @@ function feed(n: number, withArt: (i: number) => boolean): Dump[] {
// Strictly decreasing heat, so the ranking is the index order.
createdAt: new Date(Date.now() - (i + 1) * HOUR),
richContent: withArt(i)
? { type: "link", url: "https://x", thumbnailUrl: "https://x/t.png" }
? { type: "generic", url: "https://x", thumbnailUrl: "https://x/t.png" }
: undefined,
}));
}
@@ -66,7 +66,7 @@ describe("hasThumbnail / hasQuote", () => {
expect(hasThumbnail(makeDump({ thumbnailMime: "image/webp" }))).toBe(true);
expect(
hasThumbnail(
makeDump({ richContent: { type: "x", url: "u", thumbnailUrl: "t" } }),
makeDump({ richContent: { type: "generic", url: "u", thumbnailUrl: "t" } }),
),
).toBe(true);
expect(hasThumbnail(makeDump())).toBe(false);