"""Dump the PDB info stream so we know exactly which acclient.exe build
matches our PDB GUID. The PDB header points to stream 1 ("PDB Info") which
contains: u32 version, u32 signature(timestamp), u32 age, 16-byte GUID.

Usage:
    py tools/pdb-extract/dump_pdb_info.py refs/acclient.pdb
"""

import struct
import sys
import datetime
import uuid


def _ceil_div(a, b):
    return (a + b - 1) // b


def main():
    if len(sys.argv) < 2:
        print("usage: dump_pdb_info.py <path-to-pdb>")
        sys.exit(1)

    pdb_path = sys.argv[1]
    with open(pdb_path, "rb") as f:
        data = f.read()

    magic = b"Microsoft C/C++ MSF 7.00\r\n\x1aDS\x00\x00\x00"
    assert data.startswith(magic), "not an MSF 7.00 PDB"

    block_size = struct.unpack_from("<I", data, 0x20)[0]
    num_blocks = struct.unpack_from("<I", data, 0x28)[0]
    num_dir_bytes = struct.unpack_from("<I", data, 0x2C)[0]
    block_map_addr = struct.unpack_from("<I", data, 0x34)[0]

    print(f"block_size      = {block_size}")
    print(f"num_blocks      = {num_blocks}")
    print(f"num_dir_bytes   = {num_dir_bytes}")
    print(f"block_map_addr  = {block_map_addr}")

    def read_page(idx):
        return data[idx * block_size : (idx + 1) * block_size]

    dir_pages_needed = _ceil_div(num_dir_bytes, block_size)
    block_map = read_page(block_map_addr)
    dir_page_indices = struct.unpack_from(f"<{dir_pages_needed}I", block_map, 0)
    dir_data = bytearray()
    for pi in dir_page_indices:
        dir_data.extend(read_page(pi))
    dir_data = bytes(dir_data)

    num_streams = struct.unpack_from("<I", dir_data, 0)[0]
    stream_sizes = struct.unpack_from(f"<{num_streams}I", dir_data, 4)
    print(f"num_streams     = {num_streams}")

    offset = 4 + num_streams * 4
    streams = []
    for sz in stream_sizes:
        if sz == 0xFFFFFFFF:
            streams.append((0, []))
            continue
        n_pages = _ceil_div(sz, block_size)
        pages = struct.unpack_from(f"<{n_pages}I", dir_data, offset)
        offset += n_pages * 4
        streams.append((sz, list(pages)))

    # Stream 1 = PDB Info Stream
    pdb_info_size, pdb_info_pages = streams[1]
    print(f"pdb_info_size   = {pdb_info_size}")

    pdb_info = bytearray()
    for pi in pdb_info_pages:
        pdb_info.extend(read_page(pi))
    pdb_info = bytes(pdb_info[:pdb_info_size])

    version = struct.unpack_from("<I", pdb_info, 0)[0]
    signature = struct.unpack_from("<I", pdb_info, 4)[0]
    age = struct.unpack_from("<I", pdb_info, 8)[0]
    guid_bytes = pdb_info[12:28]
    pdb_guid = uuid.UUID(bytes_le=guid_bytes)

    sig_dt = datetime.datetime.fromtimestamp(signature, tz=datetime.timezone.utc)

    print()
    print("=== PDB Info Stream ===")
    print(f"version    = {version}")
    print(f"signature  = 0x{signature:08x}  ({signature})")
    print(f"  -> linker timestamp UTC: {sig_dt.isoformat()}")
    print(f"age        = {age}")
    print(f"GUID       = {{{pdb_guid}}}")
    print()
    print("This is the GUID + age the matching acclient.exe must reference")
    print("in its CodeView entry. Find a binary whose linker timestamp")
    print(f"is around {sig_dt.strftime('%Y-%m-%d')}.")


if __name__ == "__main__":
    main()