quak helper fix-missing-thumbnails --file on an empty cache stops fetching collections once it finds every file (closes #223)

`helper fix-missing-thumbnails --file` used to wait for a refresh, which
on an empty cache fetched the files of every collection. It now finds the
named files through the new `freshFilesByID` in `src/cli-read.ts`, by the
rule `freshFile` follows. On an empty cache it reads the collection list,
then one collection's files at a time, and stores none of the collections
or file records it reads. It searches the most recently updated
collection first. So a file in several albums is still named after the
first of them that `Library.albums.list()` lists. `fixMissingThumbnails`
now takes the records the command found, and fetches each original
through `lib.originalOf()`.

Model: opus-5-5

src/cli-commands.ts

@@ -37,9 +37,16 @@ import {
     thumbnailName,
 } from "./cli-output.js";
 import { type Log, logRefresh } from "./cli-log.js";
-import { freshCollections, freshFiles, freshFile } from "./cli-read.js";
+import {
+    cachedFilesByID,
+    freshCollections,
+    freshFiles,
+    freshFile,
+    freshFilesByID,
+} from "./cli-read.js";
 import { withExtension } from "./filename.js";
 import { runMetadataBackup } from "./metadata-backup.js";
+import type { Collection, EnteFile } from "./model/types.js";
 import { listMissingThumbnails, fixMissingThumbnails } from "./thumbnails.js";
 
 export interface CliContext {
@@ -133,8 +140,9 @@ const readLibraryClient = (client: Client): LibraryClient => ({
 // not start downloading the whole account. No refresh starts as the library
 // opens or on a timer. Each command asks for the refresh it needs.
 // `collections` and `files` with a collection ID need none (issues #210 and
-// #217). Nor do `get` and `get-thumb` on an empty cache (issue #222). While a
-// refresh runs, each collection whose files it has fetched is logged, so a
+// #217). Nor do `get` and `get-thumb` on an empty cache (issue #222). Nor does
+// `helper fix-missing-thumbnails --file` on an empty cache (issue #223). While
+// a refresh runs, each collection whose files it has fetched is logged, so a
 // large account shows progress rather than nothing.
 const openReadLibrary = (ctx: CliContext, client: Client): Promise<Library> =>
     Library.open({
@@ -565,10 +573,13 @@ export const fixMissingThumbnailsCommand = async (
     }
     const lib = await openReadLibrary(ctx, client);
     try {
-        // Refresh first so files added since the cache was written are found;
-        // a failed refresh throws.
-        await lib.fresh();
-        if (fileIDs.length === 0) {
+        let found: Map<number, { file: EnteFile; collection: Collection }>;
+        if (fileIDs.length > 0) {
+            found = await freshFilesByID(lib, fileIDs);
+        } else {
+            // Refresh first so files added since the cache was written are
+            // checked; a failed refresh throws.
+            await lib.fresh();
             ctx.log("info", "Scanning for missing thumbnails...");
             const missing = await listMissingThumbnails(
                 lib,
@@ -581,12 +592,14 @@ export const fixMissingThumbnailsCommand = async (
                 return 0;
             }
             ctx.log("info", `Found ${fileIDs.length} file(s) to fix.`);
+            found = cachedFilesByID(lib, fileIDs);
         }
 
         const results = await fixMissingThumbnails(
             lib,
             client,
             fileIDs,
+            found,
             (msg, level) => ctx.log(level ?? "info", msg),
         );
 

src/cli-read.ts

@@ -12,6 +12,8 @@
 // list too, then that one collection's files through `Library.freshFiles()`
 // (issue #217). On an empty cache, `get` and `get-thumb` read that list, then
 // one collection's files at a time, until they find the file (issue #222).
+// `helper fix-missing-thumbnails --file` does the same until it finds every
+// file it names (issue #223).
 //
 // `collections` and `files` with a collection ID list in the server's order.
 // `files` without one lists in the library's own enumeration order
@@ -90,3 +92,59 @@ export const freshFile = async (
     }
     return undefined;
 };
+
+// The most recently updated collection first, and the higher ID first on a
+// tie. `Library.albums.list()` lists albums in this order.
+const byNewestCollection = (a: Collection, b: Collection): number =>
+    b.updationTime - a.updationTime || b.id - a.id;
+
+// Each file named by `fileIDs` that the cache holds, mapped to its record and
+// the collection it was found in. Collections are searched in
+// `byNewestCollection` order, and a file is found in the first that holds it.
+// So `helper fix-missing-thumbnails` names a file after the same album as
+// `helper list-missing-thumbnails`. It reads the cache alone, so the caller
+// refreshes first.
+export const cachedFilesByID = (
+    lib: FreshReadLibrary,
+    fileIDs: number[],
+): Map<number, { file: EnteFile; collection: Collection }> => {
+    const wanted = new Set(fileIDs);
+    const found = new Map<number, { file: EnteFile; collection: Collection }>();
+    const collections = [...lib.listCollections()].sort(byNewestCollection);
+    for (const collection of collections) {
+        for (const file of lib.listFiles(collection.id)) {
+            if (wanted.has(file.id) && !found.has(file.id)) {
+                found.set(file.id, { file, collection });
+            }
+        }
+    }
+    return found;
+};
+
+// Each file named by `fileIDs` as the server holds it now, mapped to its record
+// and collection as `cachedFilesByID` maps it. When the cache holds the
+// account's collections, it refreshes and looks the files up in the cache. On
+// an empty cache, it reads the collection list, then one collection's files at
+// a time, and stops once it has found every file. That search stores nothing.
+export const freshFilesByID = async (
+    lib: FreshReadLibrary,
+    fileIDs: number[],
+): Promise<Map<number, { file: EnteFile; collection: Collection }>> => {
+    // Only a refresh stores collections, so a cache holding any holds them all.
+    if (lib.listCollections().length > 0) {
+        await lib.fresh();
+        return cachedFilesByID(lib, fileIDs);
+    }
+    const wanted = new Set(fileIDs);
+    const found = new Map<number, { file: EnteFile; collection: Collection }>();
+    const collections = await lib.freshCollections();
+    for (const collection of [...collections].sort(byNewestCollection)) {
+        if (found.size === wanted.size) break;
+        for (const file of await lib.freshFiles(collection)) {
+            if (wanted.has(file.id) && !found.has(file.id)) {
+                found.set(file.id, { file, collection });
+            }
+        }
+    }
+    return found;
+};

src/thumbnails.ts

@@ -5,7 +5,7 @@ import type { Client } from "./client.js";
 import type { Library } from "./library/index.js";
 import { ApiError } from "./api/client.js";
 import { encryptBlob, toBase64 } from "./crypto/index.js";
-import type { EnteFile } from "./model/types.js";
+import type { Collection, EnteFile } from "./model/types.js";
 
 // The server refuses a thumbnail larger than the one it already records for the
 // file (`thumbnail.size`, the encrypted size), so these encodings are tried
@@ -226,16 +226,18 @@ const encryptThumbnailWithin = (
     return undefined;
 };
 
-// Regenerate and upload a thumbnail for each requested file. Originals are read
-// through the library's content cache (`photo.original()`); the generated
-// thumbnail is JPEG-encoded, encrypted under the file's own key, and registered
-// with the server — the encrypt-and-upload path is unchanged. Each file is
+// Regenerate and upload a thumbnail for each requested file. `found` holds the
+// record of each requested file that a collection holds, and the collection it
+// was found in. Each original is read through the library's content cache, by
+// `lib.originalOf(file)`. The new thumbnail is a JPEG, encrypted under the
+// file's own key. It is uploaded, then registered with the server. Each file is
 // resolved to one outcome (fixed / skipped / failed) and a failure on one file
 // never stops the others.
 export const fixMissingThumbnails = async (
     lib: Library,
     client: Client,
     fileIDs: number[],
+    found: Map<number, { file: EnteFile; collection: Collection }>,
     onProgress?: ProgressCallback,
 ): Promise<ThumbnailFixResult[]> => {
     const log = onProgress ?? (() => {});
@@ -243,31 +245,8 @@ export const fixMissingThumbnails = async (
     const api = client.getApiClient();
     const { userID } = client.whoami();
 
-    // Resolve each requested fileID to its file record and owning album by
-    // enumerating the library, each file taken from the first album that holds
-    // it. The raw `EnteFile` carries the per-file key the thumbnail is
-    // encrypted under, which the projected records deliberately do not.
-    const wanted = new Set(fileIDs);
-    const fileMap = new Map<
-        number,
-        { file: EnteFile; collectionName: string }
-    >();
-    for (const album of lib.albums.list()) {
-        for (const photo of album.photos.list()) {
-            if (!wanted.has(photo.fileID) || fileMap.has(photo.fileID))
-                continue;
-            const file = lib.getFile(album.collectionID, photo.fileID);
-            if (file) {
-                fileMap.set(photo.fileID, {
-                    file,
-                    collectionName: album.name,
-                });
-            }
-        }
-    }
-
     for (const fileID of fileIDs) {
-        const entry = fileMap.get(fileID);
+        const entry = found.get(fileID);
         if (!entry) {
             results.push({
                 fileID,
@@ -279,7 +258,8 @@ export const fixMissingThumbnails = async (
             continue;
         }
 
-        const { file, collectionName } = entry;
+        const { file } = entry;
+        const collectionName = entry.collection.name;
         const title = file.metadata.title;
 
         const skipReason = reasonToSkip(file, userID);
@@ -297,15 +277,10 @@ export const fixMissingThumbnails = async (
         const maxSize = file.thumbnail.size!;
 
         try {
-            const photo = lib.photos.byID({ fileID });
-            if (!photo) {
-                throw new Error("file not present in the library cache");
-            }
-
             log(
                 `[${collectionName}] Downloading ${title} for thumbnail generation...`,
             );
-            const { path } = await photo.original();
+            const { path } = await lib.originalOf(file);
             const fileBytes = new Uint8Array(readFileSync(path));
 
             if (!isJpeg(fileBytes)) {