#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""Read the IDENTITY the client resolved for every card it currently holds.

READ-ONLY. /proc/PID/mem is opened 'rb'; there is no write path in this file.

WHY THIS EXISTS
---------------
Card identity does not come from us. Every item object in every response is
inserted into the CardsDb map by the item-parser tail (0x18014115b -> registrar
vtable +0xa08 = 0x18011cca0, a find-or-INSERT). Just before registering, the
client runs a LOCAL merge (FUN_180141660 -> FUN_180135890 for player cards) that
queries its own `players` table by

    playerid = resourceId & 0xffffff

On a HIT it fills the name and face and leaves our rating/position/attributes
alone. On a MISS it hard-writes a fixed generic card. Those MISS constants are a
FINGERPRINT, and that is what makes this probe useful: the resolved record is
sitting in the map, so one read tells us hit-or-miss for EVERY id we have served,
without opening a single card in the UI.

    MISS => rating 0x32 (50), teamid 0x78d (1933), nation 0xe (14),
            position 2 (RWB), attributes all 1, name " "

That is exactly what a player photographed in a pack on 2026-08-04: two named
cards (ids from VERIFIED_ASSET_IDS) beside three blanks at 50 RWB with every
attribute 1. So the fingerprint is confirmed live, not just read out of Ghidra.

WHAT THIS BUYS
--------------
A bulk oracle. Serving N candidate playerids and reading this once classifies all
N at a time, instead of one id per screenshot. That is the difference between
validating a 79-card pool and validating a database.

OFFSETS, AND HOW MUCH TO TRUST THEM
-----------------------------------
Record base = node + 0x28, size 0x158, copied field-by-field by FUN_1800515e0.
Offsets below were derived in Ghidra from the card view-model FUN_1800d7920 and
the parser's stack record, and cross-checked by a second agent. They are NOT yet
confirmed against a live process -- which is precisely what this tool does. Read
the report critically the first time: if `name` is garbage for a card you KNOW
renders correctly in the UI, the offset is wrong, not the game.

Usage:
    python3 card_identity_probe.py              # table + summary
    python3 card_identity_probe.py --raw        # + hexdump of the first record
    python3 card_identity_probe.py --json out.json
"""
import argparse
import json
import struct
import sys

import watch_club_model as W

REC = 0x28               # node -> record
F_ID = 0x08              # map key: the item's `id` (atom 0x15c)
F_RESOURCE = 0x18        # resourceId (atom 0x287) -- the DB key lives in the low 24 bits
F_PLAYERID = 0x1C        # written by FUN_180135890 as resourceId & 0xffffff
F_ASSET = 0x20           # assetId (atom 0x23) -- parsed, then never read by the merge
F_SUBTYPE = 0x50         # cardsubtypeid (atom 0x6c)
F_CARDTYPE = 0x4C        # FUN_1800d8330(subtype); 1 = player => the merge runs
F_TEAM = 0x94            # MISS writes 0x78d
F_ATTRS = (0x98, 0x9C, 0xA0, 0xA4, 0xA8, 0xAC)   # MISS writes 1 to each
F_RATING = 0xB4          # MISS writes 0x32
F_NAME_FIRST = 0xB8
F_NAME_LAST = 0xC8
F_NAME_KNOWN = 0xDD      # 0x1f bytes
F_POSITION = 0x146       # MISS writes 2
F_NATION = 0x148         # MISS writes 0xe
F_LEAGUE = 0x154         # filled from the DB on a hit
REC_LEN = 0x158

MISS = {"rating": 0x32, "teamid": 0x78D, "nation": 0xE, "position": 2}


def cstr(buf, off, maxlen=0x1F):
    """Inline char array -> str. Names are stored in the record itself, not
    interned: three arrays at +0xb8/+0xc8/+0xdd, no string table."""
    if buf is None or off + 1 > len(buf):
        return ""
    end = min(off + maxlen, len(buf))
    raw = buf[off:end].split(b"\x00", 1)[0]
    return raw.decode("utf-8", "replace").strip()


def u8(b, o):
    return b[o] if b and o < len(b) else None


def u16(b, o):
    return struct.unpack_from("<H", b, o)[0] if b and o + 2 <= len(b) else None


def u32(b, o):
    return struct.unpack_from("<I", b, o)[0] if b and o + 4 <= len(b) else None


def nodes(mem, obj, limit=W.MAX_NODES):
    """[node_addr] for every node in the card tree. Same defensive DFS as
    watch_club_model.walk_tree -- both child slots, visited set, bounded."""
    root = mem.q(obj + W.TREE_ROOT)
    end = obj + W.TREE_END
    if root is None or root == 0 or root == end:
        return []
    out, seen, stack = [], set(), [root]
    while stack and len(out) < limit:
        p = stack.pop()
        if not p or p == end or p in seen or (p & 7):
            continue
        seen.add(p)
        out.append(p)
        for slot in (W.NODE_A, W.NODE_B):
            c = mem.q(p + slot)
            if c and c != end and c not in seen:
                stack.append(c)
    return out


def read_card(mem, node):
    buf = mem.read(node + REC, REC_LEN)
    if buf is None or len(buf) < REC_LEN:
        return None
    res = u32(buf, F_RESOURCE)
    c = {
        "node": node,
        "id": u32(buf, F_ID),
        "resourceId": res,
        "playerid": res & 0xFFFFFF if res is not None else None,
        "playerid_field": u32(buf, F_PLAYERID),
        "assetId": u32(buf, F_ASSET),
        "cardtype": u32(buf, F_CARDTYPE),
        "subtype": u32(buf, F_SUBTYPE),
        "teamid": u32(buf, F_TEAM),
        "rating": u8(buf, F_RATING),
        "position": u8(buf, F_POSITION),
        "nation": u16(buf, F_NATION),
        "league": u32(buf, F_LEAGUE),
        "attrs": [u8(buf, o) for o in F_ATTRS],
        "first": cstr(buf, F_NAME_FIRST, 0x10),
        "last": cstr(buf, F_NAME_LAST, 0x15),
        "known": cstr(buf, F_NAME_KNOWN, 0x1F),
        "_raw": buf,
    }
    c["verdict"] = classify(c)
    return c


def classify(c):
    """HIT / MISS / NO-MERGE, from the fingerprint the binary writes.

    NO-MERGE matters as much as the other two: if cardsubtypeid is absent the
    record defaults to 0x156 -> cardtype 0 -> FUN_180141660 skips the merge
    entirely, so the card shows OUR raw JSON and never consults the DB. That
    looks nothing like a MISS and must not be reported as one.
    """
    if c["cardtype"] != 1:
        return "NO-MERGE"
    if all(c[k] == v for k, v in MISS.items()) and all(a == 1 for a in c["attrs"]):
        return "MISS"
    name = (c["known"] or c["last"] or c["first"]).strip()
    return "HIT" if name else "MISS?"


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--raw", action="store_true", help="hexdump the first record")
    ap.add_argument("--json", metavar="PATH", help="write the full table as JSON")
    ap.add_argument("--limit", type=int, default=W.MAX_NODES)
    a = ap.parse_args()

    pid = W.find_pid()
    if pid is None:
        print("FIFA17.exe is not running.")
        return 1
    base = W.dll_base(pid)
    if base is None:
        print("pid %d is up but %s is not mapped yet." % (pid, W.DLL))
        return 1
    mem = W.Mem(pid)
    obj = mem.q(base + (W.G_CARDSDB - W.IMG_BASE))
    if not obj:
        print("CardsDb singleton is NULL (no FUT session loaded).")
        return 1
    size = mem.i32(obj + W.TREE_SIZE)
    ns = nodes(mem, obj, a.limit)
    print("pid=%d  cardsdll=%#x  CardsDb=%#x  size(+0x160e8)=%s  walked=%d"
          % (pid, base, obj, size, len(ns)))
    if size is not None and size != len(ns):
        print("  !! walk disagrees with the size counter -- trust the counter, "
              "the walk went wrong")

    cards = [c for c in (read_card(mem, n) for n in ns) if c]
    cards.sort(key=lambda c: (c["resourceId"] or 0))

    print()
    print("%-11s %-10s %-8s %-4s %-4s %-6s %-4s %-18s %s"
          % ("id", "resource", "playerid", "rat", "pos", "team", "nat", "name", "verdict"))
    for c in cards:
        nm = (c["known"] or ("%s %s" % (c["first"], c["last"])).strip())[:18]
        print("%-11s %-10s %-8s %-4s %-4s %-6s %-4s %-18s %s"
              % (c["id"], c["resourceId"], c["playerid"], c["rating"], c["position"],
                 c["teamid"], c["nation"], nm, c["verdict"]))

    tally = {}
    for c in cards:
        tally[c["verdict"]] = tally.get(c["verdict"], 0) + 1
    print("\n" + "  ".join("%s=%d" % kv for kv in sorted(tally.items())))

    hits = sorted({c["playerid"] for c in cards if c["verdict"] == "HIT"})
    miss = sorted({c["playerid"] for c in cards if c["verdict"] in ("MISS", "MISS?")})
    if hits:
        print("\nplayerids PRESENT in the client's DB (%d): %s"
              % (len(hits), ", ".join(str(h) for h in hits)))
    if miss:
        print("\nplayerids ABSENT (%d): %s"
              % (len(miss), ", ".join(str(m) for m in miss)))

    if a.raw and cards:
        b = cards[0]["_raw"]
        print("\nrecord %#x:" % (cards[0]["node"] + REC))
        for off in range(0, REC_LEN, 16):
            row = b[off:off + 16]
            print("  +%03x  %-47s  %s" % (
                off, " ".join("%02x" % x for x in row),
                "".join(chr(x) if 32 <= x < 127 else "." for x in row)))

    if a.json:
        for c in cards:
            c.pop("_raw", None)
        with open(a.json, "w") as f:
            json.dump(cards, f, indent=1)
        print("\nwrote %s" % a.json)

    print("\nfailed reads=%d" % mem.fails)
    return 0


if __name__ == "__main__":
    sys.exit(main())