| 1 | import { deflateSync, gzipSync } from "node:zlib"; |
| 2 | import { describe, expect, it } from "vitest"; |
| 3 | import { hashObject, parsePack, sha1 } from "../src/index.js"; |
| 4 | |
| 5 | // Packs from clients must not run a repository's Durable Object out of memory (128 MB) or tie it up |
| 6 | // for minutes, however small the pack is. |
| 7 | |
| 8 | const header = (type: number, size: number) => { |
| 9 | const out: number[] = []; |
| 10 | let c = (type << 4) | (size & 15); |
| 11 | size = Math.floor(size / 16); |
| 12 | while (size > 0) { |
| 13 | out.push(c | 0x80); |
| 14 | c = size & 0x7f; |
| 15 | size = Math.floor(size / 128); |
| 16 | } |
| 17 | out.push(c); |
| 18 | return out; |
| 19 | }; |
| 20 | const varint = (n: number) => { |
| 21 | const out: number[] = []; |
| 22 | do { |
| 23 | let b = n % 128; |
| 24 | n = Math.floor(n / 128); |
| 25 | if (n > 0) b |= 0x80; |
| 26 | out.push(b); |
| 27 | } while (n > 0); |
| 28 | return out; |
| 29 | }; |
| 30 | const hex = (oid: string) => Buffer.from(oid, "hex"); |
| 31 | |
| 32 | /** A pack from entries already encoded (header, any base, zlib data). */ |
| 33 | async function pack(entries: Uint8Array[]): Promise<Uint8Array> { |
| 34 | const head = Buffer.alloc(12); |
| 35 | head.write("PACK"); |
| 36 | head.writeUInt32BE(2, 4); |
| 37 | head.writeUInt32BE(entries.length, 8); |
| 38 | const body = Buffer.concat([head, ...entries]); |
| 39 | return new Uint8Array(Buffer.concat([body, await sha1(body)])); |
| 40 | } |
| 41 | const blob = (content: Uint8Array, z = deflateSync) => Buffer.concat([Buffer.from(header(3, content.length)), z(content)]); |
| 42 | const refDelta = (base: string, delta: Uint8Array) => Buffer.concat([Buffer.from(header(7, delta.length)), hex(base), deflateSync(delta)]); |
| 43 | /** A delta that replaces a base of `from` bytes with `to`. */ |
| 44 | const replace = (from: number, to: Uint8Array) => Uint8Array.from([...varint(from), ...varint(to.length), to.length, ...to]); |
| 45 | |
| 46 | describe("pack limits", () => { |
| 47 | it("resolves a long delta chain in one pass, whatever order the pack lists it in", async () => { |
| 48 | // 20,000 REF_DELTAs, each against the one before it, listed newest first: resolving them by |
| 49 | // repeated passes over the unresolved ones took minutes. |
| 50 | const n = 20_000; |
| 51 | const content = (i: number) => Buffer.from(String(i).padStart(8, "0")); |
| 52 | const oids = [await hashObject("blob", content(0))]; |
| 53 | for (let i = 1; i <= n; i++) oids.push(await hashObject("blob", content(i))); |
| 54 | const entries: Uint8Array[] = []; |
| 55 | for (let i = n; i >= 1; i--) entries.push(refDelta(oids[i - 1]!, replace(8, content(i)))); |
| 56 | entries.push(blob(content(0))); |
| 57 | const p = await pack(entries); |
| 58 | const started = Date.now(); |
| 59 | const objects = await parsePack(p); |
| 60 | expect(Date.now() - started).toBeLessThan(10_000); |
| 61 | expect(objects).toHaveLength(n + 1); |
| 62 | expect(new Set(objects.map((o) => o.oid))).toEqual(new Set(oids)); |
| 63 | }, 30_000); |
| 64 | |
| 65 | it("counts what each object costs in memory, not only its content", async () => { |
| 66 | // 20,000 one-byte blobs are a 240 KB pack but cost far more than 240 KB to hold. |
| 67 | const entries: Uint8Array[] = []; |
| 68 | for (let i = 0; i < 20_000; i++) entries.push(blob(Buffer.from([i & 255, i >> 8]))); |
| 69 | const p = await pack(entries); |
| 70 | await expect(parsePack(p, undefined, { maxHeldBytes: 1024 * 1024 })).rejects.toThrow(/memory/); |
| 71 | expect(await parsePack(p, undefined, { maxHeldBytes: 64 * 1024 * 1024 })).toHaveLength(20_000); |
| 72 | }); |
| 73 | |
| 74 | it("refuses a small pack whose objects inflate past the memory budget", async () => { |
| 75 | // 25 blobs just under the 4 MiB that is kept compressed: under 200 KB of pack, about 100 MB held. |
| 76 | const size = 4 * 1024 * 1024 - 1024; |
| 77 | const entries: Uint8Array[] = []; |
| 78 | for (let i = 0; i < 25; i++) { |
| 79 | const b = Buffer.alloc(size); |
| 80 | b[0] = i; |
| 81 | entries.push(blob(b)); |
| 82 | } |
| 83 | const p = await pack(entries); |
| 84 | expect(p.length).toBeLessThan(250 * 1024); |
| 85 | await expect(parsePack(p, undefined, { largeObjectBytes: 4 * 1024 * 1024 })).rejects.toThrow(/memory/); |
| 86 | }); |
| 87 | |
| 88 | it("refuses a delta whose declared result can't be held, before allocating it", async () => { |
| 89 | const base = Buffer.from("base"); |
| 90 | const delta = Uint8Array.from([...varint(base.length), ...varint(300 * 1024 * 1024), 4, ...base]); |
| 91 | const p = await pack([blob(base), refDelta(await hashObject("blob", base), delta)]); |
| 92 | await expect(parsePack(p)).rejects.toThrow(/delta result of \d+ bytes is larger/); |
| 93 | }); |
| 94 | |
| 95 | it("counts a thin pack's bases from the repository, once each", async () => { |
| 96 | const base = Buffer.alloc(2 * 1024 * 1024, 7); |
| 97 | const oid = await hashObject("blob", base); |
| 98 | let reads = 0; |
| 99 | const external = async (o: string) => (o === oid ? (reads++, { type: "blob" as const, content: base }) : null); |
| 100 | const deltas: Uint8Array[] = []; |
| 101 | for (let i = 0; i < 3; i++) deltas.push(refDelta(oid, replace(base.length, Buffer.from(`v${i}`)))); |
| 102 | const p = await pack(deltas); |
| 103 | await expect(parsePack(p, external, { maxBytes: 1024 * 1024 })).rejects.toThrow(/unpacks to more than/); |
| 104 | reads = 0; |
| 105 | expect(await parsePack(p, external, { maxBytes: 4 * 1024 * 1024 })).toHaveLength(3); |
| 106 | expect(reads).toBe(1); |
| 107 | }); |
| 108 | |
| 109 | it("refuses gzip data where git has zlib", async () => { |
| 110 | const content = Buffer.from("hello\n"); |
| 111 | await expect(parsePack(await pack([blob(content, gzipSync)]))).rejects.toThrow(/zlib|header/); |
| 112 | const large = Buffer.alloc(64 * 1024, 1); |
| 113 | await expect(parsePack(await pack([blob(large, gzipSync)]), undefined, { largeObjectBytes: 1024 })).rejects.toThrow(/zlib|header/); |
| 114 | }); |
| 115 | }); |