T-HUB/packages/core/src/file-names.ts
glass beadian e7e703c105 Integrate group files: nullable room for uploads, archive class, claim idempotency, upload route
Wires the three parallel group-cloud tracks to one surface and fixes the
seams between them:

- chat_media_archive.room_id becomes nullable (direct web uploads have no
  Matrix room yet — the contract's null-event pattern extends to the room);
  core GroupFile.roomId and ArchiveEntryInput.roomId follow.
- mime_class gains 'archive' (zip) across the 029 CHECK, validation
  MIME_CLASSES and the bot classifier — one vocabulary everywhere.
- registerArchiveEntry claim keys are null-safe for room-less uploads.
- New: POST /files/groups/:groupId/upload — FileInterceptor (20 MiB) streams
  through magic-byte sniffing, library-safe naming, oCIS upload and the
  metadata index, behind group-membership ACL (Owner/Admin bypass).
- safeFileName/sniffMime promoted to packages/core (file-names.ts,
  file-mime.ts) so the bot and the api share one implementation; the bot's
  local modules become re-export shims; @types/node added to core.

Verified: api typecheck clean, group-files 22/22, bot 74/74, web typecheck
clean; 029 re-applied clean on a fresh scratch DB (room_id nullable,
archive class, claim_key unique all confirmed in the catalog).
2026-10-11 10:09:24 +00:00

44 lines
1.5 KiB
TypeScript

export const MAX_SAFE_NAME_BYTES = 120;
const FALLBACK = "attachment";
const WINDOWS_RESERVED = /^(con|prn|aux|nul|com[0-9]|lpt[0-9])(\..*)?$/i;
function truncateUtf8(text: string, maxBytes: number): string {
let out = "";
for (const ch of text) {
if (Buffer.byteLength(out + ch, "utf8") > maxBytes) break;
out += ch;
}
return out;
}
/**
* Library-safe single path segment: no directories, control or reserved
* characters, leading dots, or unbounded length. Extension is preserved when
* truncating; a sniffed extension is appended when the name has none.
*/
export function safeFileName(raw: string, sniffedExtension: string | null = null): string {
const basename = raw.normalize("NFKC").split(/[/\\]/).pop() ?? "";
let name = basename
.replace(/[\p{Cc}\p{Cf}]/gu, "")
.replace(/[<>:"|?*#%{}^~[\]`]/g, "_")
.replace(/\s+/g, " ")
.replace(/_+/g, "_")
.trim()
.replace(/^[.\s_-]+/, "")
.replace(/[.\s]+$/, "");
if (name === "") name = FALLBACK;
if (WINDOWS_RESERVED.test(name)) name = `_${name}`;
const dot = name.lastIndexOf(".");
let stem = dot > 0 ? name.slice(0, dot) : name;
let ext = dot > 0 ? name.slice(dot + 1).toLowerCase() : "";
if (ext === "" && sniffedExtension !== null) ext = sniffedExtension;
if (Buffer.byteLength(ext, "utf8") > 16) {
stem = name;
ext = sniffedExtension ?? "";
}
const suffix = ext === "" ? "" : `.${ext}`;
stem = truncateUtf8(stem, MAX_SAFE_NAME_BYTES - Buffer.byteLength(suffix, "utf8")).trim();
if (stem === "") stem = FALLBACK;
return `${stem}${suffix}`;
}