v3: fix migration 0011 mistaking real og:images for favicons

0011 tested for "favicon" anywhere in the path, so mirtitles.org's declared
og:image — /wp-content/uploads/2022/04/mir-logo-favicon.png — was moved into
faviconUrl and its thumbnailUrl cleared. Without a thumbnail, hasThumbnail() is
false and the journal mosaic demoted the dump from an image card to a
pull-quote. A blanket .svg match did the same to real artwork (tanibis.net's
header.svg).

0012 judges an icon by its filename rather than the whole path: named
favicon…/apple-touch-icon…/icon…, living in an icons/ directory, or ending in
.ico. That spares mir-logo-favicon.png and also catches icon_SEARCH.png, which
0011 missed. It runs in both directions, and is deliberately narrow when
reversing — a value is only promoted back to thumbnailUrl if it matched 0011's
rule but not this one, so rows written by a normal fetch aren't disturbed.

On the dev database: 4 thumbnails restored, 1 icon reclassified, real favicons
left alone, and a second pass rewrites nothing.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

api/db/migrate.ts

@@ -10,6 +10,7 @@ import { up as up0008ChatMessages } from "./migrations/0008_chat_messages.ts";
 import { up as up0009ChatReply } from "./migrations/0009_chat_reply.ts";
 import { up as up0010YoutubeEmbedStart } from "./migrations/0010_youtube_embed_start.ts";
 import { up as up0011SplitFaviconThumbnail } from "./migrations/0011_split_favicon_thumbnail.ts";
+import { up as up0012FixFaviconReclassification } from "./migrations/0012_fix_favicon_reclassification.ts";
 
 interface Migration {
   name: string;
@@ -31,6 +32,10 @@ const MIGRATIONS: Migration[] = [
   { name: "0009_chat_reply", up: up0009ChatReply },
   { name: "0010_youtube_embed_start", up: up0010YoutubeEmbedStart },
   { name: "0011_split_favicon_thumbnail", up: up0011SplitFaviconThumbnail },
+  {
+    name: "0012_fix_favicon_reclassification",
+    up: up0012FixFaviconReclassification,
+  },
 ];
 
 export function runMigrations(db: DatabaseSync): void {

api/db/migrations/0012_fix_favicon_reclassification.ts

@@ -0,0 +1,100 @@
+import type { DatabaseSync } from "node:sqlite";
+
+// Repairs 0011, which was too eager about what counts as a site icon.
+//
+// 0011 tested for "favicon" anywhere in the path, so a legitimate `og:image`
+// like mirtitles.org's `/wp-content/uploads/2022/04/mir-logo-favicon.png` was
+// moved into `faviconUrl` and its `thumbnailUrl` cleared — which also demoted
+// the dump from an image card to a pull-quote in the journal mosaic. A blanket
+// `.svg` match had the same effect on real artwork.
+//
+// `isIconUrl` here looks at the *filename* rather than the whole path: an icon
+// is named `favicon…`, `apple-touch-icon…` or `icon…`, lives in an `icons/`
+// directory, or ends in `.ico`. That both spares `mir-logo-favicon.png` and
+// catches `icon_SEARCH.png`, which 0011 missed.
+//
+// Applied in both directions, and deliberately narrow when reversing: a value
+// is only promoted back to `thumbnailUrl` if it matches 0011's rule but not
+// this one, so rows written by a normal fetch aren't disturbed.
+
+/** 0011's rule, kept verbatim so its false positives can be identified. */
+function wasIconUrl0011(raw: string): boolean {
+  let pathname: string;
+  try {
+    pathname = new URL(raw).pathname;
+  } catch {
+    return false;
+  }
+  return /favicon|apple-touch-icon|\/icons?\//i.test(pathname) ||
+    /\.(ico|svg)$/i.test(pathname);
+}
+
+/** Whether a URL names a site icon, judged on its filename and directory. */
+function isIconUrl(raw: string): boolean {
+  let pathname: string;
+  try {
+    pathname = new URL(raw).pathname;
+  } catch {
+    return false;
+  }
+  const segments = pathname.split("/").filter(Boolean);
+  const filename = segments.pop() ?? "";
+  if (/\.ico$/i.test(filename)) return true;
+  if (segments.some((s) => /^(favicons?|icons?)$/i.test(s))) return true;
+  const basename = filename.replace(/\.[^.]+$/, "");
+  return /^(favicon|apple-touch-icon|icon)(?=$|[-_.\d])/i.test(basename);
+}
+
+export function up(db: DatabaseSync): void {
+  const rows = db.prepare(
+    `SELECT id, rich_content FROM dumps
+      WHERE kind = 'url' AND rich_content IS NOT NULL;`,
+  ).all() as { id: string; rich_content: string }[];
+
+  const update = db.prepare(
+    `UPDATE dumps SET rich_content = ? WHERE id = ?;`,
+  );
+
+  let restored = 0;
+  let reclassified = 0;
+  for (const row of rows) {
+    let rich: { thumbnailUrl?: string; faviconUrl?: string };
+    try {
+      rich = JSON.parse(row.rich_content);
+    } catch {
+      continue; // malformed payload — leave it untouched
+    }
+
+    // Artwork 0011 mistook for an icon: put it back.
+    if (
+      rich.faviconUrl && !rich.thumbnailUrl &&
+      wasIconUrl0011(rich.faviconUrl) && !isIconUrl(rich.faviconUrl)
+    ) {
+      const { faviconUrl: _dropped, ...rest } = rich;
+      update.run(
+        JSON.stringify({ ...rest, thumbnailUrl: rich.faviconUrl }),
+        row.id,
+      );
+      restored++;
+      continue;
+    }
+
+    // An icon 0011's rule didn't recognize: move it now.
+    if (
+      rich.thumbnailUrl && !rich.faviconUrl && isIconUrl(rich.thumbnailUrl)
+    ) {
+      const { thumbnailUrl: _dropped, ...rest } = rich;
+      update.run(
+        JSON.stringify({ ...rest, faviconUrl: rich.thumbnailUrl }),
+        row.id,
+      );
+      reclassified++;
+    }
+  }
+
+  if (restored > 0 || reclassified > 0) {
+    console.log(
+      `[migrate] 0012: restored ${restored} thumbnail(s), reclassified ${reclassified} icon(s)`,
+    );
+  }
+}