Files
quak/src/download/index.ts
T
clawbot 8f575550af
check / check (push) Successful in 41s
Durable atomic writer with fsync and per-chunk download progress (closes #39)
The atomic writer fsyncs the staged temp file before rename and the directory after, and is exported for reuse. downloadFile/downloadThumbnail gain an optional per-chunk onProgress hook (non-decreasing, final equals bytesWritten; no-op when absent). Retry and TAG_FINAL checks unchanged.

Model: opus-4-8
2026-09-22 12:01:06 +02:00

237 lines
9.2 KiB
TypeScript

import { randomUUID } from "node:crypto";
import { open, rename, rm } from "node:fs/promises";
import { dirname, join } from "node:path";
import {
fromBase64,
initStreamPull,
pullStreamChunk,
STREAM_CHUNK_OVERHEAD,
STREAM_CHUNK_SIZE,
streamTagFinal,
} from "../crypto/index.js";
import { TruncatedStreamError } from "../errors.js";
import { withRetry } from "../retry.js";
import type { ApiClient } from "../api/client.js";
import type { EnteFile } from "../model/types.js";
export interface DownloadResult {
path: string;
bytesWritten: number;
}
// Fired as decrypted plaintext accumulates, with the running total of
// plaintext bytes recovered so far. Within one download it is non-decreasing
// and its last value equals the final `bytesWritten`. A retry restarts the
// file from byte zero (see `fetchAndDecrypt`), so a fresh attempt begins its
// own count from zero.
export type ProgressCallback = (bytesDone: number) => void;
const ENC_CHUNK_SIZE = STREAM_CHUNK_SIZE + STREAM_CHUNK_OVERHEAD;
const streamDecrypt = async (
stream: ReadableStream<Uint8Array>,
header: Uint8Array,
key: Uint8Array,
onProgress?: ProgressCallback,
): Promise<Uint8Array> => {
const state = initStreamPull(header, key);
const reader = stream.getReader();
let buffer = new Uint8Array(0);
const plainChunks: Uint8Array[] = [];
let totalPlain = 0;
let chunksPulled = 0;
let lastTag = -1;
for (;;) {
const { done, value } = await reader.read();
if (value) {
const merged = new Uint8Array(buffer.length + value.length);
merged.set(buffer);
merged.set(value, buffer.length);
buffer = merged;
}
while (buffer.length >= ENC_CHUNK_SIZE) {
const encChunk = buffer.slice(0, ENC_CHUNK_SIZE);
buffer = buffer.slice(ENC_CHUNK_SIZE);
const { plaintext, tag } = pullStreamChunk(state, encChunk);
plainChunks.push(plaintext);
totalPlain += plaintext.length;
chunksPulled++;
lastTag = tag;
onProgress?.(totalPlain);
}
if (done) {
if (buffer.length > 0) {
// Whatever is left over once every whole chunk has been
// consumed must be the stream's final chunk, and a final
// chunk that actually arrived in full authenticates. If it
// does not, the body stopped part-way through a chunk — the
// ordinary shape of a dropped connection. Poly1305 cannot
// tell a partial chunk from a corrupt one, so this is
// reported as the truncation it almost always is, with the
// authentication failure kept as the error's cause.
let pulled;
try {
pulled = pullStreamChunk(state, buffer);
} catch (err) {
throw new TruncatedStreamError(
`download: stream truncated: response body ended with ${buffer.length} trailing bytes that did not authenticate as a final chunk (transfer stopped mid-chunk, or the data is corrupt)`,
{ cause: err },
);
}
plainChunks.push(pulled.plaintext);
totalPlain += pulled.plaintext.length;
chunksPulled++;
lastTag = pulled.tag;
onProgress?.(totalPlain);
}
break;
}
}
// Only the last chunk of a secretstream carries TAG_FINAL. Everything a
// dropped connection did deliver still decrypts and authenticates, so the
// absence of TAG_FINAL is the only evidence that the body was cut short.
// Returning a short plaintext here would put a corrupt file on disk that
// later backup runs would treat as complete.
if (chunksPulled === 0) {
throw new TruncatedStreamError(
"download: stream truncated: response body contained no secretstream chunks",
);
}
const tagFinal = streamTagFinal();
if (lastTag !== tagFinal) {
throw new TruncatedStreamError(
`download: stream truncated: last chunk tag ${lastTag}, expected TAG_FINAL (${tagFinal})`,
);
}
const result = new Uint8Array(totalPlain);
let offset = 0;
for (const chunk of plainChunks) {
result.set(chunk, offset);
offset += chunk.length;
}
return result;
};
// Write `plaintext` to `destination` atomically and durably: stage it in a
// temporary sibling file (same directory, so the rename cannot cross a
// filesystem boundary) and rename it into place. Callers therefore never
// observe a partially written destination, and a pre-existing file at that
// path is replaced only once the new contents are complete on disk.
//
// Durability against a power cut needs two fsyncs. Without them the write can
// return while the data or the rename is still only in the kernel's page
// cache, and a crash then resurrects an empty renamed file — exactly the
// corruption a later backup run treats as a complete download. So the temp
// file's contents are fsynced before the rename, and the containing directory
// is fsynced after it, so both the bytes and the new directory entry are on
// stable storage before this returns.
//
// Exported so the metadata store can reuse the same durable write.
export const writeAtomic = async (
destination: string,
plaintext: Uint8Array,
): Promise<void> => {
const dir = dirname(destination);
// The random suffix keeps concurrent downloads of the same destination
// from stepping on each other's temporary file.
const tmpPath = join(dir, `.quak-${randomUUID()}.tmp`);
try {
const handle = await open(tmpPath, "w");
try {
await handle.writeFile(plaintext);
await handle.sync();
} finally {
await handle.close();
}
await rename(tmpPath, destination);
// Fsync the directory so the rename itself survives a crash: renaming
// over a synced temp file still leaves the new directory entry in the
// page cache until the directory is synced.
const dirHandle = await open(dir, "r");
try {
await dirHandle.sync();
} finally {
await dirHandle.close();
}
} catch (err) {
// Best-effort cleanup. A failure to remove the temporary file must
// never replace the error that actually explains what went wrong.
await rm(tmpPath, { force: true }).catch(() => undefined);
throw err;
}
};
// Fetch a stream and decrypt it, retrying the whole sequence.
//
// The request is only the first third of a download. `getXStream` returns as
// soon as headers arrive, and the bytes are pulled here, so a socket reset
// mid-body — the dominant failure mode for multi-megabyte photos over a CDN —
// throws in `streamDecrypt` and never reaches `ApiClient` at all. Retrying the
// request alone would miss it entirely.
//
// The client's own retry is therefore switched off for these two calls: with
// both layers active the budgets would multiply, and the library default of
// four attempts would mean sixteen requests for one file. The policy comes
// from the client so a caller that configured one gets it here too.
//
// A retry starts the file over from byte zero: the secretstream pull state is
// not resumable and there is no Range support on these endpoints.
const fetchAndDecrypt = async (
api: ApiClient,
openStream: () => Promise<ReadableStream<Uint8Array>>,
header: Uint8Array,
key: Uint8Array,
onProgress?: ProgressCallback,
): Promise<Uint8Array> =>
withRetry(async () => {
const stream = await openStream();
return streamDecrypt(stream, header, key, onProgress);
}, api.getRetryOptions());
export const downloadFile = async (
api: ApiClient,
file: EnteFile,
outPath?: string,
onProgress?: ProgressCallback,
): Promise<DownloadResult> => {
const resolvedPath = outPath ?? file.metadata.title;
const header = fromBase64(file.file.decryptionHeader);
const plaintext = await fetchAndDecrypt(
api,
() => api.getFileStream(file.id, { retry: false }),
header,
file.key,
onProgress,
);
// Outside the retry, deliberately: only the attempt that produced a
// complete, authenticated plaintext gets to stage a temporary file, so a
// download that needed three tries still performs exactly one write and
// one rename.
await writeAtomic(resolvedPath, plaintext);
return { path: resolvedPath, bytesWritten: plaintext.length };
};
export const downloadThumbnail = async (
api: ApiClient,
file: EnteFile,
outPath?: string,
onProgress?: ProgressCallback,
): Promise<DownloadResult> => {
const resolvedPath = outPath ?? `thumb_${file.metadata.title}`;
const header = fromBase64(file.thumbnail.decryptionHeader);
const plaintext = await fetchAndDecrypt(
api,
() => api.getThumbnailStream(file.id, { retry: false }),
header,
file.key,
onProgress,
);
await writeAtomic(resolvedPath, plaintext);
return { path: resolvedPath, bytesWritten: plaintext.length };
};