fix: Dont rearchive singlefile uploads and consider them as archives

2 files changed, 13 insertions, 4 deletions

diff --git a/apps/web/components/dashboard/preview/LinkContentSection.tsx b/apps/web/components/dashboard/preview/LinkContentSection.tsx
index f09cc31f..f1fe3820 100644
--- a/apps/web/components/dashboard/preview/LinkContentSection.tsx
+++ b/apps/web/components/dashboard/preview/LinkContentSection.tsx
@@ -26,10 +26,12 @@ import {
 } from "@hoarder/shared/types/bookmarks";
 
 function FullPageArchiveSection({ link }: { link: ZBookmarkedLink }) {
+  const archiveAssetId =
+    link.fullPageArchiveAssetId ?? link.precrawledArchiveAssetId;
   return (
     <iframe
       title={link.url}
-      src={`/api/assets/${link.fullPageArchiveAssetId}`}
+      src={`/api/assets/${archiveAssetId}`}
       className="relative h-full min-w-full"
     />
   );
@@ -199,7 +201,10 @@ export default function LinkContentSection({
             </SelectItem>
             <SelectItem
               value="archive"
-              disabled={!bookmark.content.fullPageArchiveAssetId}
+              disabled={
+                !bookmark.content.fullPageArchiveAssetId &&
+                !bookmark.content.precrawledArchiveAssetId
+              }
             >
               {t("common.archive")}
             </SelectItem>
diff --git a/apps/workers/crawlerWorker.ts b/apps/workers/crawlerWorker.ts
index 91adb185..7611494e 100644
--- a/apps/workers/crawlerWorker.ts
+++ b/apps/workers/crawlerWorker.ts
@@ -669,7 +669,8 @@ async function crawlAndParseUrl(
       .set({
         title: meta.title,
         description: meta.description,
-        imageUrl: meta.image,
+        // Don't store data URIs as they're not valid URLs and are usually quite large
+        imageUrl: meta.image?.startsWith("data:") ? null : meta.image,
         favicon: meta.logo,
         content: readableContent?.textContent,
         htmlContent: readableContent?.content,
@@ -705,7 +706,10 @@ async function crawlAndParseUrl(
   ]);
 
   return async () => {
-    if (serverConfig.crawler.fullPageArchive || archiveFullPage) {
+    if (
+      !precrawledArchiveAssetId &&
+      (serverConfig.crawler.fullPageArchive || archiveFullPage)
+    ) {
       const {
         assetId: fullPageArchiveAssetId,
         size,