Give backup album folders distinct names and remove stale entries (closes #103)

Within a collection's folder, files whose sanitized titles match (ignoring
case) each get their file ID added before the extension, and collections
whose sanitized names match get their ID added, so no symlink or JSON
replaces another. Names are chosen across all collections, so a scoped run
names folders the same as a full one.

Each run first removes symlinks into originals/ that no longer belong to a
collection, and the folders quak wrote (a sibling JSON with an album ID) for
collections that are gone or renamed. Anything else is left alone; a folder
still holding user files keeps its JSON.

Model: opus-5-5

README.md

@@ -492,6 +492,20 @@ failure still exits non-zero.
         <name>.json             collection metadata + file list
 ```
 
+A collection's directory and JSON are named after the collection, and a symlink
+after the file's title, both with unsafe characters replaced. When two
+collections would get the same name, or two files in one collection the same
+title (ignoring case in both), each of them gets its ID added: two albums named
+`Trip` become `Trip (10)/` and `Trip (11)/`, and two files titled `IMG_0001.JPG`
+become `IMG_0001 (12345).JPG` and `IMG_0001 (12346).JPG`. IDs never change, so a
+name stays the same from run to run until such a clash appears or goes away.
+
+Each run removes the symlinks into `originals/` that no longer belong in their
+collection's directory, and the directories (and JSON) of collections that were
+deleted or renamed. Nothing else in `collections/` is touched: a file or a
+symlink you put there stays, and a directory that still holds one after its
+symlinks are removed stays too, with its JSON.
+
 Each file is downloaded exactly once regardless of how many collections it
 appears in. On subsequent runs, existing originals are skipped. If a download
 fails, the error is logged and the backup continues with the next file. The exit

TODO.md

@@ -18,6 +18,13 @@ Tag v1.0.0.
 
 # Completed Steps
 
+- 2026-09-23: Fixed the backup's per-collection folders (issue 103). Two files
+  in one collection with the same title, and two collections with the same name,
+  each get their ID added to the name (`IMG_0001 (12345).JPG`, `Trip (10)/`), so
+  none replaces another's symlink or JSON. Each run removes symlinks into
+  `originals/` for files no longer in the collection, and the folders of deleted
+  or renamed collections, leaving anything else in `collections/` alone. The
+  README backup layout states the naming rule.
 - 2026-09-23: Single-sourced the version string (issue 5). `package.json` is the
   only place it is written: `src/index.ts` imports it for `VERSION` and
   `bin/quak.ts` passes `VERSION` to commander. tsc copies `package.json` to

src/backup.ts

@@ -17,7 +17,9 @@
 // temp-then-rename, so a file that exists is whole and is never re-fetched — an
 // interrupted run resumes by listing the directory. The derived views hold no
 // unique state, so they are rebuilt every run; that repairs stale sidecars and
-// missing or broken symlinks left by an earlier crash.
+// missing or broken symlinks left by an earlier crash. A rebuild also removes
+// the symlinks into originals/ that no longer belong to an album, and the
+// directories of albums that no longer exist.
 //
 // Resilience (issue #8): no per-file condition aborts the run. A failed
 // download or a failed symlink is caught, recorded in `failures.json` with a
@@ -34,13 +36,14 @@ import {
     readdirSync,
     readFileSync,
     readlinkSync,
+    rmdirSync,
     rmSync,
     statSync,
     symlinkSync,
     writeFileSync,
 } from "node:fs";
 import { copyFile, rename, rm } from "node:fs/promises";
-import { basename, dirname, join, relative } from "node:path";
+import { basename, dirname, extname, join, relative } from "node:path";
 
 import { fsyncPath } from "./download/index.js";
 import { safeExtension, sanitizeFileName } from "./filename.js";
@@ -227,6 +230,83 @@ const rebuildSymlink = (linkPath: string, target: string): void => {
     symlinkSync(target, linkPath);
 };
 
+// The on-disk names for the entries of one directory, keyed by ID. Each name
+// is used as is unless another entry has the same name, ignoring case (two
+// names that differ only in case are one entry on a case-insensitive file
+// system); then every entry sharing it gets ` (<id>)`, before the extension
+// when `beforeExtension` is set. IDs are stable, so the names are too.
+const namesByID = (
+    entries: { id: number; name: string }[],
+    beforeExtension: boolean,
+): Map<number, string> => {
+    const counts = new Map<string, number>();
+    for (const { name } of entries) {
+        const key = name.toLowerCase();
+        counts.set(key, (counts.get(key) ?? 0) + 1);
+    }
+    const names = new Map<number, string>();
+    for (const { id, name } of entries) {
+        if (counts.get(name.toLowerCase()) === 1) {
+            names.set(id, name);
+            continue;
+        }
+        const ext = beforeExtension ? extname(name) : "";
+        const stem = name.slice(0, name.length - ext.length);
+        names.set(id, `${stem} (${id})${ext}`);
+    }
+    return names;
+};
+
+// Remove the symlinks in the album directory `dir` that point into
+// `originalsDir` and are not named in `keep`. Nothing else in the directory
+// is touched: anything else there was put there by the user.
+const removeStaleLinks = (
+    dir: string,
+    keep: Set<string>,
+    originalsDir: string,
+): void => {
+    const target = relative(dir, originalsDir);
+    for (const name of readdirSync(dir)) {
+        if (keep.has(name)) continue;
+        const path = join(dir, name);
+        if (
+            lstatSync(path).isSymbolicLink() &&
+            dirname(readlinkSync(path)) === target
+        ) {
+            rmSync(path);
+        }
+    }
+};
+
+// Remove the directories under `collectionsDir` that an earlier run wrote for
+// an album that is gone or renamed: a directory not named in `current` with a
+// `<name>.json` beside it holding an album ID, which is what a run writes. Its
+// symlinks into originals/ are removed; if that leaves it empty, it and its
+// JSON are deleted, otherwise both stay for what the user put there.
+const removeStaleAlbumDirs = (
+    collectionsDir: string,
+    current: Set<string>,
+    originalsDir: string,
+): void => {
+    for (const entry of readdirSync(collectionsDir, { withFileTypes: true })) {
+        if (!entry.isDirectory() || current.has(entry.name)) continue;
+        const jsonPath = join(collectionsDir, `${entry.name}.json`);
+        try {
+            const album = JSON.parse(readFileSync(jsonPath, "utf-8")) as {
+                id?: unknown;
+            };
+            if (typeof album.id !== "number") continue;
+        } catch {
+            continue;
+        }
+        const dir = join(collectionsDir, entry.name);
+        removeStaleLinks(dir, new Set(), originalsDir);
+        if (readdirSync(dir).length > 0) continue;
+        rmdirSync(dir);
+        rmSync(jsonPath);
+    }
+};
+
 const loadLedger = (path: string): Map<number, FailureEntry> => {
     const ledger = new Map<number, FailureEntry>();
     try {
@@ -303,9 +383,10 @@ export const runBackup = async (
 
     // Collections in scope, and the distinct files across them (a file shared
     // by two albums is one original).
-    const collections = lib
-        .listCollections()
-        .filter((c) => (only ? only.has(c.name) : true));
+    const allCollections = lib.listCollections();
+    const collections = allCollections.filter((c) =>
+        only ? only.has(c.name) : true,
+    );
     const collectionName = new Map<number, string>();
     for (const c of collections) collectionName.set(c.id, c.name);
 
@@ -406,23 +487,55 @@ export const runBackup = async (
         }
     }
 
-    // Then the per-collection symlink trees and JSON.
+    // Then the per-collection symlink trees and JSON. Directory names are
+    // chosen across every album, not just those in scope, so a scoped run
+    // names an album the same as a full one and never takes the directory of
+    // an album it skipped. Stale entries are removed before anything is
+    // rebuilt, so on a case-insensitive file system removing an old name can
+    // never remove the new one.
+    const albumDirNames = namesByID(
+        allCollections.map((c) => ({
+            id: c.id,
+            name: sanitizeFileName(c.name, `collection-${c.id}`),
+        })),
+        false,
+    );
+    try {
+        removeStaleAlbumDirs(
+            collectionsDir,
+            new Set(albumDirNames.values()),
+            originalsDir,
+        );
+    } catch (err) {
+        log(`FAILED removing old album directories: ${errorMessage(err)}`);
+    }
+
     for (const c of collections) {
-        const colDirName = sanitizeFileName(c.name, `collection-${c.id}`);
+        const colDirName = albumDirNames.get(c.id)!;
         const colDir = join(collectionsDir, colDirName);
         mkdirSync(colDir, { recursive: true });
 
         const files = filesByCollection.get(c.id) ?? [];
+        const linkNames = namesByID(
+            files.map((f) => ({
+                id: f.id,
+                name: sanitizeFileName(f.metadata.title, `file-${f.id}`),
+            })),
+            true,
+        );
+        try {
+            removeStaleLinks(colDir, new Set(linkNames.values()), originalsDir);
+        } catch (err) {
+            log(`FAILED removing old links in ${c.name}: ${errorMessage(err)}`);
+        }
+
         const metaFiles: { id: number; metadata: EnteFile["metadata"] }[] = [];
         for (const file of files) {
             metaFiles.push({ id: file.id, metadata: file.metadata });
             if (!includeOriginals) continue;
             const orig = join(originalsDir, originalName(file));
             if (!isPresent(orig)) continue;
-            const linkName = sanitizeFileName(
-                file.metadata.title,
-                `file-${file.id}`,
-            );
+            const linkName = linkNames.get(file.id)!;
             const linkPath = join(colDir, linkName);
             try {
                 rebuildSymlink(linkPath, relative(colDir, orig));

test/cli/backup.test.ts

@@ -40,6 +40,7 @@ import {
     readFileSync,
     readlinkSync,
     rmSync,
+    symlinkSync,
     writeFileSync,
 } from "node:fs";
 import { spawnSync } from "node:child_process";
@@ -47,6 +48,7 @@ import { join } from "node:path";
 import { tmpdir } from "node:os";
 import { describe, it, expect, beforeEach, afterEach, vi } from "vitest";
 
+import { runBackup, type BackupLibrary } from "../../src/backup.js";
 import { Library } from "../../src/library/index.js";
 import type { ContentSource } from "../../src/library/content.js";
 import type { CollectionsPage, FilesPage } from "../../src/client.js";
@@ -622,3 +624,172 @@ describe("lib.backup", () => {
         lib.close();
     });
 });
+
+// The album folders under collections/, driven through `runBackup` with a
+// stand-in library whose albums a test changes between runs.
+describe("backup album folders", () => {
+    interface Album {
+        collection: Collection;
+        files: EnteFile[];
+    }
+
+    const libraryOf = (albums: Album[]): BackupLibrary => ({
+        refresh: async () => {},
+        listCollections: () => albums.map((a) => a.collection),
+        listFiles: (id) =>
+            albums.find((a) => a.collection.id === id)?.files ?? [],
+        original: async (fileID) => {
+            const path = join(root, `source-${fileID}`);
+            writeFileSync(path, `original ${fileID}`);
+            return { path };
+        },
+        thumbnail: async () => {
+            throw new Error("no thumbnails in this stand-in");
+        },
+    });
+
+    // Every entry under collections/, one level of directories deep, with each
+    // symlink's target.
+    const tree = (outDir: string): string[] => {
+        const lines: string[] = [];
+        const list = (dir: string, prefix: string): void => {
+            for (const name of readdirSync(dir).sort()) {
+                const path = join(dir, name);
+                const st = lstatSync(path);
+                if (st.isSymbolicLink()) {
+                    lines.push(`${prefix}${name} -> ${readlinkSync(path)}`);
+                } else if (st.isDirectory() && prefix === "") {
+                    lines.push(`${name}/`);
+                    list(path, `${name}/`);
+                } else {
+                    lines.push(`${prefix}${name}`);
+                }
+            }
+        };
+        list(join(outDir, "collections"), "");
+        return lines;
+    };
+
+    const albumID = (outDir: string, jsonName: string): number =>
+        JSON.parse(readFileSync(join(outDir, "collections", jsonName), "utf-8"))
+            .id;
+
+    it("gives every file and every album its own name when names repeat", async () => {
+        const outDir = join(root, "backup");
+        const lib = libraryOf([
+            {
+                collection: collection(10, "Trip"),
+                files: [
+                    file(1, 10, "IMG_0001.JPG"),
+                    file(2, 10, "IMG_0001.JPG"),
+                    file(4, 10, "img_0001.jpg"),
+                    file(3, 10, "other.jpg"),
+                ],
+            },
+            {
+                collection: collection(11, "Trip"),
+                files: [file(3, 11, "other.jpg")],
+            },
+        ]);
+
+        const result = await runBackup(lib, { downloadDirectory: outDir });
+
+        expect(result.failed).toBe(0);
+        expect(tree(outDir)).toEqual([
+            "Trip (10)/",
+            "Trip (10)/IMG_0001 (1).JPG -> ../../originals/1.JPG",
+            "Trip (10)/IMG_0001 (2).JPG -> ../../originals/2.JPG",
+            "Trip (10)/img_0001 (4).jpg -> ../../originals/4.jpg",
+            "Trip (10)/other.jpg -> ../../originals/3.jpg",
+            "Trip (10).json",
+            "Trip (11)/",
+            "Trip (11)/other.jpg -> ../../originals/3.jpg",
+            "Trip (11).json",
+        ]);
+        expect(albumID(outDir, "Trip (10).json")).toBe(10);
+        expect(albumID(outDir, "Trip (11).json")).toBe(11);
+    });
+
+    it("changes nothing on a second run over an unchanged account", async () => {
+        const outDir = join(root, "backup");
+        const lib = libraryOf([
+            {
+                collection: collection(10, "Trip"),
+                files: [
+                    file(1, 10, "IMG_0001.JPG"),
+                    file(2, 10, "IMG_0001.JPG"),
+                ],
+            },
+            {
+                collection: collection(11, "Trip"),
+                files: [file(3, 11, "other.jpg")],
+            },
+        ]);
+
+        await runBackup(lib, { downloadDirectory: outDir });
+        const before = tree(outDir);
+        const second = await runBackup(lib, { downloadDirectory: outDir });
+
+        expect(second.downloaded).toBe(0);
+        expect(second.failed).toBe(0);
+        expect(tree(outDir)).toEqual(before);
+    });
+
+    it("removes links and album folders that are gone, and nothing the user added", async () => {
+        const outDir = join(root, "backup");
+        const albums: Album[] = [
+            {
+                collection: collection(10, "Trip"),
+                files: [
+                    file(1, 10, "IMG_0001.JPG"),
+                    file(2, 10, "IMG_0001.JPG"),
+                    file(3, 10, "other.jpg"),
+                ],
+            },
+            {
+                collection: collection(12, "Work"),
+                files: [file(5, 12, "a.jpg")],
+            },
+            {
+                collection: collection(13, "Old"),
+                files: [file(5, 13, "a.jpg")],
+            },
+        ];
+        const lib = libraryOf(albums);
+        await runBackup(lib, { downloadDirectory: outDir });
+
+        // What the user put in the tree: a note and a symlink of their own in
+        // an album, a note in an album about to be renamed, and a folder quak
+        // did not create.
+        const collectionsDir = join(outDir, "collections");
+        writeFileSync(join(collectionsDir, "Trip", "notes.txt"), "mine");
+        symlinkSync("../elsewhere", join(collectionsDir, "Trip", "mine"));
+        writeFileSync(join(collectionsDir, "Work", "keep.txt"), "mine");
+        mkdirSync(join(collectionsDir, "Mine"));
+        writeFileSync(join(collectionsDir, "Mine", "keep.txt"), "mine");
+
+        // File 2 leaves Trip, Work is renamed Office, Old is deleted.
+        albums[0]!.files.splice(1, 1);
+        albums[1]!.collection = collection(12, "Office");
+        albums.splice(2, 1);
+        const result = await runBackup(lib, { downloadDirectory: outDir });
+
+        expect(result.failed).toBe(0);
+        expect(tree(outDir)).toEqual([
+            "Mine/",
+            "Mine/keep.txt",
+            "Office/",
+            "Office/a.jpg -> ../../originals/5.jpg",
+            "Office.json",
+            "Trip/",
+            "Trip/IMG_0001.JPG -> ../../originals/1.JPG",
+            "Trip/mine -> ../elsewhere",
+            "Trip/notes.txt",
+            "Trip/other.jpg -> ../../originals/3.jpg",
+            "Trip.json",
+            "Work/",
+            "Work/keep.txt",
+            "Work.json",
+        ]);
+    });
+});