fix(worker): fetch packed header region for encoded-header 7z ranged listing

worker/src/archive/ranged/sevenz-ranged.test.ts

@@ -63,3 +63,67 @@ describe("readSevenZListingRanged", () => {
     expect(entries === null || Array.isArray(entries)).toBe(true);
   });
 });
+
+import { read7zNumber, locate7zEncodedHeaderPack } from "./sevenz-ranged.js";
+
+describe("read7zNumber", () => {
+  it("reads a single-byte number", () => {
+    expect(read7zNumber(Buffer.from([0x2a]), 0)).toEqual({ value: 42, next: 1 });
+  });
+  it("reads a two-byte number (first-byte length mask + LE trailing byte)", () => {
+    // 1000 = 0x03E8: low byte 0xE8, high nibble 0x03 -> first = 0x80|0x03 = 0x83, trailing 0xE8
+    expect(read7zNumber(Buffer.from([0x83, 0xe8]), 0)).toEqual({ value: 1000, next: 2 });
+    // 500 = 0x01F4 -> first 0x81, trailing 0xF4
+    expect(read7zNumber(Buffer.from([0x81, 0xf4]), 0)).toEqual({ value: 500, next: 2 });
+  });
+});
+
+describe("locate7zEncodedHeaderPack", () => {
+  it("parses PackPos and summed PackSize from an encoded header", () => {
+    // kEncodedHeader, kPackInfo, PackPos=1000([0x83,0xe8]), NumStreams=1([0x01]),
+    // kSize, PackSize=500([0x81,0xf4])
+    const enc = Buffer.from([0x17, 0x06, 0x83, 0xe8, 0x01, 0x09, 0x81, 0xf4]);
+    expect(locate7zEncodedHeaderPack(enc)).toEqual({ packPos: 1000, packSize: 500 });
+  });
+  it("returns null for a plain (kHeader 0x01) header", () => {
+    expect(locate7zEncodedHeaderPack(Buffer.from([0x01, 0x04]))).toBeNull();
+  });
+  it("sums multiple pack streams", () => {
+    // PackPos=0([0x00]), NumStreams=2([0x02]), kSize, sizes 10([0x0a]) + 20([0x14])
+    const enc = Buffer.from([0x17, 0x06, 0x00, 0x02, 0x09, 0x0a, 0x14]);
+    expect(locate7zEncodedHeaderPack(enc)).toEqual({ packPos: 0, packSize: 30 });
+  });
+});
+
+describe("readSevenZListingRanged (encoded header)", () => {
+  it("fetches the mid-file packed-header region as a third read", async () => {
+    const size = 5_000_000;
+    const nextHeaderOffset = 4_000_000;      // relative to end of 32-byte sig header
+    const endStart = 32 + nextHeaderOffset;  // absolute
+    const packPos = 1000;                    // relative to end of sig header
+    const packStart = 32 + packPos;          // absolute
+    const packSize = 500;
+    const sig = Buffer.alloc(32);
+    Buffer.from([0x37, 0x7a, 0xbc, 0xaf, 0x27, 0x1c]).copy(sig, 0);
+    sig.writeBigUInt64LE(BigInt(nextHeaderOffset), 12);
+    sig.writeBigUInt64LE(8n, 20); // NextHeaderSize = 8 (the encoded-header descriptor below)
+    const encHeader = Buffer.from([0x17, 0x06, 0x83, 0xe8, 0x01, 0x09, 0x81, 0xf4]);
+
+    const reads: { offset: number; length: number }[] = [];
+    const read = async (_id: string, offset: number, length: number) => {
+      reads.push({ offset, length });
+      if (offset === 0) return sig.subarray(0, length);
+      if (offset === endStart) return encHeader.subarray(0, length);
+      return Buffer.alloc(length, 0xcd); // stand-in packed-header bytes
+    };
+
+    const entries = await readSevenZListingRanged(
+      [{ fileId: "1", fileSize: BigInt(size), fileName: "a.7z" }],
+      read,
+    );
+    expect(reads[0]).toEqual({ offset: 0, length: 32 });
+    expect(reads[1]).toEqual({ offset: endStart, length: 8 });
+    expect(reads[2]).toEqual({ offset: packStart, length: packSize });
+    expect(entries === null || Array.isArray(entries)).toBe(true);
+  });
+});

worker/src/archive/ranged/sevenz-ranged.ts

@@ -8,6 +8,55 @@ const log = childLogger("sevenz-ranged");
 
 const SEVENZ_MAGIC = Buffer.from([0x37, 0x7a, 0xbc, 0xaf, 0x27, 0x1c]);
 
+const K_HEADER = 0x01;
+const K_ENCODED_HEADER = 0x17;
+const K_PACK_INFO = 0x06;
+const K_SIZE = 0x09;
+
+/** Read a 7z variable-length number: first byte is a length mask, followed by
+ *  little-endian bytes. Math.pow keeps values exact above 2^31. */
+export function read7zNumber(buf: Buffer, pos: number): { value: number; next: number } {
+  const first = buf[pos];
+  let mask = 0x80;
+  let value = 0;
+  let p = pos + 1;
+  for (let i = 0; i < 8; i++) {
+    if ((first & mask) === 0) {
+      value += (first & (mask - 1)) * Math.pow(2, 8 * i);
+      return { value, next: p };
+    }
+    if (p >= buf.length) throw new RangeError("7z number overruns buffer");
+    value += buf[p] * Math.pow(2, 8 * i);
+    p++;
+    mask >>= 1;
+  }
+  return { value, next: p };
+}
+
+/** For an encoded (kEncodedHeader) 7z next-header, return the absolute-ish
+ *  location of the packed header stream(s): PackPos (relative to end of the
+ *  32-byte signature header) and the summed PackSize. Null if not encoded or
+ *  the StreamsInfo doesn't start with PackInfo as expected. */
+export function locate7zEncodedHeaderPack(
+  nextHeader: Buffer,
+): { packPos: number; packSize: number } | null {
+  let p = 0;
+  if (nextHeader[p] !== K_ENCODED_HEADER) return null;
+  p++;
+  if (nextHeader[p] !== K_PACK_INFO) return null;
+  p++;
+  const packPos = read7zNumber(nextHeader, p); p = packPos.next;
+  const numStreams = read7zNumber(nextHeader, p); p = numStreams.next;
+  if (nextHeader[p] !== K_SIZE) return null;
+  p++;
+  let total = 0;
+  for (let i = 0; i < numStreams.value; i++) {
+    const s = read7zNumber(nextHeader, p); p = s.next;
+    total += s.value;
+  }
+  return { packPos: packPos.value, packSize: total };
+}
+
 export function parseSevenZSignatureHeader(
   buf: Buffer,
 ): { nextHeaderOffset: number; nextHeaderSize: number } | null {
@@ -35,17 +84,26 @@ export async function readSevenZListingRanged(
     const endStart = 32 + parsed.nextHeaderOffset;
     if (endStart < 0 || endStart + parsed.nextHeaderSize > size) return null;
     const endHeader = await read(part.fileId, endStart, parsed.nextHeaderSize, part.fileSize);
-    return listFromSparse(
+
-      [{
+    const regions = [
-        fileName: part.fileName,
-        size,
-        regions: [
       { offset: 0, bytes: sig },
       { offset: endStart, bytes: endHeader },
-        ],
+    ];
-      }],
+
-      read7zContents,
+    const headerType = endHeader[0];
-    );
+    if (headerType === K_ENCODED_HEADER) {
+      // Compressed header: its packed bytes live mid-file, not at EOF. Fetch them.
+      const pack = locate7zEncodedHeaderPack(endHeader);
+      if (!pack) return null;
+      const packStart = 32 + pack.packPos;
+      if (packStart < 0 || packStart + pack.packSize > size) return null;
+      const packBytes = await read(part.fileId, packStart, pack.packSize, part.fileSize);
+      regions.push({ offset: packStart, bytes: packBytes });
+    } else if (headerType !== K_HEADER) {
+      return null; // unknown next-header type
+    }
+
+    return listFromSparse([{ fileName: part.fileName, size, regions }], read7zContents);
   } catch (err) {
     log.warn({ err, fileId: part.fileId }, "ranged 7z listing failed");
     return null;