feat(worker): derive a dedup identity for forward-path packages without bytes

worker/src/archive/forward-identity.test.ts

@@ -0,0 +1,30 @@
+import { describe, it, expect } from "vitest";
+import { createHash } from "crypto";
+import { deriveForwardContentHash } from "./forward-identity.js";
+import type { FileEntry } from "./zip-reader.js";
+
+function entry(crc32: string | null): FileEntry {
+  return { path: "a", fileName: "a", extension: null, compressedSize: 1n, uncompressedSize: 1n, crc32 };
+}
+
+describe("deriveForwardContentHash", () => {
+  it("hashes the sorted CRC list when all entries have a CRC32 (ZIP/RAR)", () => {
+    const entries = [entry("BBBB"), entry("AAAA")];
+    const expectedHash = createHash("sha256").update(["aaaa", "bbbb"].join(",")).digest("hex");
+    expect(deriveForwardContentHash(entries, "unique-1", "chan-1", 42n)).toBe(`fingerprint:${expectedHash}`);
+  });
+
+  it("falls back to remoteUniqueId when CRCs are incomplete (7z today)", () => {
+    const entries = [entry(null), entry("AAAA")];
+    expect(deriveForwardContentHash(entries, "unique-42", "chan-1", 42n)).toBe("forward:unique-42");
+  });
+
+  it("falls back to sourceChannelId+sourceMessageId when there's no CRC and no remoteUniqueId", () => {
+    const entries = [entry(null)];
+    expect(deriveForwardContentHash(entries, null, "chan-1", 42n)).toBe("forward:chan-1:42");
+  });
+
+  it("falls back past an empty entries list the same way", () => {
+    expect(deriveForwardContentHash([], null, "chan-1", 7n)).toBe("forward:chan-1:7");
+  });
+});

worker/src/archive/forward-identity.ts

@@ -0,0 +1,33 @@
+import { createHash } from "crypto";
+import { crcFingerprint } from "./fingerprint.js";
+import type { FileEntry } from "./zip-reader.js";
+
+/**
+ * Derive a Package.contentHash-compatible identity string for a forward-path
+ * package (no downloaded bytes exist to hash directly). Priority order:
+ *   1. A CRC32-fingerprint hash, when the ranged listing's CRCs are complete
+ *      (ZIP/RAR today) — the strongest available signal, since it lets
+ *      forward-path and download-path copies of the same archive still
+ *      collide/dedupe on identical content.
+ *   2. TDLib's remote.unique_id, when CRCs are incomplete (7z today has none).
+ *   3. sourceChannelId+sourceMessageId, as a last-resort unique value so the
+ *      required-unique Package.contentHash column is always satisfiable.
+ * Follows the same `<prefix>:<value>` synthetic-hash convention already used
+ * by `rebuild.ts`'s `rebuild:${destChannelId}:${destMessageId}` placeholder.
+ */
+export function deriveForwardContentHash(
+  entries: FileEntry[],
+  remoteUniqueId: string | null,
+  sourceChannelId: string,
+  sourceMessageId: bigint,
+): string {
+  const fp = crcFingerprint(entries);
+  if (fp.complete && fp.crcs.length > 0) {
+    const hash = createHash("sha256").update(fp.crcs.join(",")).digest("hex");
+    return `fingerprint:${hash}`;
+  }
+  if (remoteUniqueId) {
+    return `forward:${remoteUniqueId}`;
+  }
+  return `forward:${sourceChannelId}:${sourceMessageId}`;
+}