Add the media downloader with hash storage and local file serving

media-scrape/src/extract.ts

@@ -13,10 +13,14 @@ const AUDIO_EXT = new Set(["mp3", "m4a", "ogg", "wav", "flac"]);
 /** Sticker formatType to file extension. 3 is Lottie JSON; not archived. */
 const STICKER_EXT: Record<number, string | undefined> = { 1: "png", 2: "apng", 4: "gif" };
 
+/** Where the item came from. Embeds are never downloaded. */
+export type MediaSource = "attachment" | "sticker" | "embed";
+
 /** A media item extracted from a message. `url` is the original source link. */
 export interface ExtractedMedia {
     kind: MediaKind;
     url: string;
+    source: MediaSource;
     provider: string | null;
     contentType: string | null;
     size: number | null;
@@ -68,6 +72,7 @@ function hostname(url: string | null): string | null {
 function extractEmbed(embed: CoreEmbed): ExtractedMedia | null {
     const provider = embed.provider ?? hostname(embed.url);
     const common = {
+        source: "embed" as const,
         provider,
         downloaded: false,
         size: null,
@@ -117,6 +122,7 @@ function extractSticker(sticker: CoreSticker): ExtractedMedia | null {
 
     return {
         kind: ext === "gif" ? "gif" : "image",
+        source: "sticker",
         url: `https://cdn.discordapp.com/stickers/${sticker.id}.${ext}`,
         provider: "discord",
         contentType: null,
@@ -138,6 +144,7 @@ function extractFrom(message: MediaMessage): ExtractedMedia[] {
         if (!kind) continue;
         items.push({
             kind,
+            source: "attachment",
             url: attachment.url,
             provider: "discord",
             contentType: attachment.contentType,