Sylpheed/tools/re-capture/submenu_focus_sweep.py

#!/usr/bin/env python3
"""Does EACH submenu remember its cursor across leave -> re-enter?

The main menu PERSISTS (focus-persists-across-title.txt); EXTRAS RESETS
(extras-focus-resets.txt). Two screens, two behaviours, so there is no menu-wide
rule and every screen has to be measured. This sweeps the three that are left:
LOAD GAME, TUTORIAL, OPTIONS.

❔ NEW GAME is deliberately NOT entered -- the corpus has held it untested
because it starts a game, and nothing here is worth breaking that for.

Controls, each of which exists because an earlier run failed without it:
  * ABSOLUTE row check after EVERY navigation press, not just the total -- a
    constant offset passes a differential control exactly
    (menu-focus-reader-offset.txt);
  * SCREEN IDENTITY against a reference frame captured in this same run -- the
    glyph window cannot separate the main menu from a submenu (327 / 324 / 317);
  * 🔴 NO RING READER INSIDE A SUBMENU. ring_row.py scans x 500:542, which is
    the MAIN MENU's gutter. EXTRAS happened to put its ring in that column;
    LOAD GAME, TUTORIAL and OPTIONS do not (their cursors move at x 97..231,
    338..1099 and 153..479), so the first sweep read a STATIC element and all
    three voided on "the ring did not move". They had moved. The decision here
    needs no ring at all: S1 and S2 differ ONLY by cursor position, so compare
    S3 to each of them over the whole frame;
  * every press confirmed from the guest's own [RE-INPUT] log.

Any control failing SKIPS that screen and moves on; it never reports a number it
cannot justify.

    submenu_focus_sweep.py LOG OUTDIR [wait_s]
"""
import os, re, subprocess, sys, time
import numpy as np
from PIL import Image

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from ring_row import ring_row, main_menu_item, is_main_menu, NAMES

LOG, OUT = sys.argv[1], sys.argv[2]
W, H = 1280, 720
PAD = os.path.join(os.path.dirname(os.path.abspath(__file__)), "pad.py")
# LOAD GAME, TUTORIAL, OPTIONS by default. Overridable so NEW GAME (0) can be
# driven for the DIFFICULTY question.
#
# ⚠️ NEW GAME IS SAFE FOR *THIS* PROBE AND ONLY THIS ONE. Its forward path --
# Ⓐ on a difficulty -> SELECT DATA -> guest throw at PC 0x82307128 -- crashes the
# game. This probe presses Ⓐ to ENTER, one DOWN, then Ⓑ to leave, and never
# presses Ⓐ inside a submenu, so it cannot reach SELECT DATA. Do not add an Ⓐ.
TARGETS = [int(x) for x in os.environ.get("SWEEP_TARGETS", "1,2,3").split(",")]
T0 = time.time()


def deliveries(vk):
    pat = re.compile((r"RE-INPUT\] XamInputGetKeystrokeEx -> user=\d+ vk=%s flags=0001" % vk).encode())
    try:
        return len(pat.findall(open(LOG, "rb").read()))
    except FileNotFoundError:
        return 0


def press(btn, vk, tries=5):
    for _ in range(tries):
        before = deliveries(vk)
        subprocess.run([sys.executable, PAD, "tap", btn, "0.5"], check=False)
        for _ in range(20):
            time.sleep(0.25)
            if deliveries(vk) > before:
                return True
    print(f"[{time.time()-T0:7.1f}s] 🔴 {btn} NEVER delivered", flush=True)
    return False


def _open():
    return subprocess.Popen(
        ["ffmpeg", "-loglevel", "error", "-f", "x11grab", "-draw_mouse", "0",
         "-video_size", f"{W}x{H}", "-i", ":98", "-r", "4",
         "-f", "rawvideo", "-pix_fmt", "rgb24", "-"],
        stdout=subprocess.PIPE, bufsize=W * H * 3 * 2)


def fresh():
    q = _open(); a = None
    for _ in range(3):
        b = q.stdout.read(W * H * 3)
        if len(b) == W * H * 3:
            a = np.frombuffer(b, np.uint8).reshape(H, W, 3).astype(int)
    q.kill()
    return a


def img(a):
    return Image.fromarray(a.astype(np.uint8))


def differs(a, b):
    return float((np.abs(a - b).max(axis=2) > 24).mean())


def glyph(a):
    r, g, bl = a[:, :, 0], a[:, :, 1], a[:, :, 2]
    return int(((g > 130) & (g - r > 45) & (g - bl > 45)).sum())


def wait_until(pred, what, limit=60):
    t = time.time()
    while time.time() - t < limit:
        a = fresh()
        if a is not None and pred(a):
            return a
    print(f"[{time.time()-T0:7.1f}s] 🔴 TIMEOUT waiting for {what}", flush=True)
    return None


os.makedirs(OUT, exist_ok=True)

# ── SELF-TEST: the decision rule must CONSTRUCT both of its verdicts ──────────
# sylpheed-port's rule, after a control of theirs carried the right NAME over the
# wrong filter: a control must construct the failure it is named after. Mine was
# one-sided -- I checked only that the rule reports RESETS on a known-RESETS
# triple, so a rule biased entirely to RESETS would have passed. Both directions
# are constructed here from the SAME frames, and the EXIT CODE is the assertion:
# printing a verdict is not asserting it.
def _verdict(a, b, c):
    cur = np.abs(a - b).max(axis=2) > 24
    if cur.sum() == 0:
        return "NO-CURSOR"
    d1 = float(np.abs(c - a).max(axis=2)[cur].mean())
    d2 = float(np.abs(c - b).max(axis=2)[cur].mean())
    return "RESETS" if d1 < d2 * 0.5 else "PERSISTS" if d2 < d1 * 0.5 else "UNDECIDED"


def _self_test():
    ref = os.environ.get("SWEEP_SELFTEST_DIR", "/sylph-home/re/extrasfocus")
    try:
        A, B, C = [np.asarray(Image.open(f"{ref}/{f}.png").convert("RGB"), dtype=int)
                   for f in ("E1", "E2", "E3")]
    except Exception as e:
        print(f"🔴 SELF-TEST UNAVAILABLE ({e}) — refusing to run", flush=True)
        sys.exit(3)
    bad = 0
    for nm, args, want in (("known RESETS (real EXTRAS triple)", (A, B, C), "RESETS"),
                           ("constructed PERSISTS", (A, B, B), "PERSISTS"),
                           ("constructed RESETS", (A, B, A), "RESETS")):
        got = _verdict(*args); ok = got == want; bad += not ok
        print(f"   {'✅' if ok else '🔴'} {nm:36} -> {got:9} (want {want})", flush=True)
    if bad:
        print("🔴 SELF-TEST FAILED — the rule cannot produce both verdicts.", flush=True)
        sys.exit(3)
    print("   ✅ self-test passed: the rule constructs both verdicts", flush=True)


print("── decision-rule self-test ──", flush=True)
_self_test()
# Verifiable WITHOUT starting a run. Without this the only way to check the
# self-test was to launch the script, which then proceeds to wait ~150 s for a
# main menu and opens x11grab captures -- so "did my self-test pass?" could not be
# answered without disturbing whatever else was using the display.
if "--selftest-only" in sys.argv:
    sys.exit(0)

MAIN = wait_until(lambda a: is_main_menu(img(a))
                  and 250 <= glyph(a) <= 420, "the main menu", 150)
if MAIN is None:
    sys.exit("never identified the main menu")
img(MAIN).save(f"{OUT}/main-ref.png")
print(f"[{time.time()-T0:7.1f}s] MAIN MENU reference, focus = "
      f"{NAMES[main_menu_item(ring_row(img(MAIN)))]}", flush=True)

results = {}
for tgt in TARGETS:
    name = NAMES[tgt]
    print(f"\n=========== {name} ===========", flush=True)
    # 🔴 NARROW test, not whole-frame. A crash dialog covering the screen centre
    # made a whole-frame identity test unable to match ever again, while the ring
    # column the dialog did not cover read correctly throughout.
    a = wait_until(lambda a: is_main_menu(img(a)),
                   "the main menu (by ring row)", 60)
    if a is None:
        print(f"   SKIP {name}: no main-menu ring row"); continue
    cur = main_menu_item(ring_row(img(a)))
    if cur is None:
        print(f"   SKIP {name}: no main-menu ring row"); continue
    ok = True
    for step in range((tgt - cur) % 5):
        if not press("DOWN", "5811"):
            ok = False; break
        time.sleep(1.2)
        y = ring_row(img(fresh())); i = main_menu_item(y)
        want = (cur + step + 1) % 5
        print(f"   step {step+1}: ring y {y} -> {NAMES[i] if i is not None else '??'} "
              f"(want {NAMES[want]})", flush=True)
        if i != want:
            print(f"   🔴 CONTROL FAILED walking to {name}"); ok = False; break
    if not ok:
        results[name] = "skipped (navigation control failed)"; continue

    if not press("A", "5800"):
        results[name] = "skipped (A not delivered)"; continue
    if wait_until(lambda x: differs(x, MAIN) > 0.20, f"{name} to open", 40) is None:
        results[name] = "skipped (A did not change the screen)"; continue
    time.sleep(3.0)
    S1 = fresh(); img(S1).save(f"{OUT}/{name.replace(' ','_')}-S1.png")
    print(f"   S1 opened: glyph {glyph(S1)}, "
          f"{100*differs(S1, MAIN):.1f}% from main", flush=True)

    if not press("DOWN", "5811"):
        results[name] = "skipped (DOWN not delivered inside)"; continue
    time.sleep(2.5)
    S2 = fresh(); img(S2).save(f"{OUT}/{name.replace(' ','_')}-S2.png")
    moved = differs(S1, S2)
    print(f"   S2 after 1 DOWN: {100*moved:.2f}% of the frame changed", flush=True)
    # CONTROL: the cursor must have moved, and by a LOCALISED amount -- a whole
    # screen changing means the DOWN left the screen, not moved a cursor.
    if moved < 0.0005:
        results[name] = f"VOID (control): nothing changed on DOWN ({100*moved:.3f}%)"
        press("B", "5801"); time.sleep(3); continue
    if moved > 0.20:
        results[name] = f"VOID (control): {100*moved:.1f}% changed — DOWN left the screen"
        press("B", "5801"); time.sleep(3); continue
    print(f"   ✅ CONTROL PASSED: a localised change ({100*moved:.2f}%)", flush=True)

    if not press("B", "5801"):
        results[name] = "skipped (B not delivered)"; continue
    if wait_until(lambda x: is_main_menu(img(x)),
                  "the main menu (by ring row)", 60) is None:
        results[name] = "VOID: B did not return to the main menu"; continue
    if not press("A", "5800"):
        results[name] = "skipped (A not delivered on re-entry)"; continue
    if wait_until(lambda x: differs(x, MAIN) > 0.20, f"{name} to reopen", 40) is None:
        results[name] = "VOID: re-entry did not change the screen"; continue
    time.sleep(3.0)
    S3 = fresh(); img(S3).save(f"{OUT}/{name.replace(' ','_')}-S3.png")
    # The pixels that changed when the cursor moved ARE the cursor's region -- no
    # per-screen geometry, which is what defeated sweep 1 (ring_row scans the MAIN
    # MENU's gutter; these screens put cursors at x 97..231, 338..1099, 153..479).
    cur = np.abs(S1 - S2).max(axis=2) > 24
    same_p95 = float(np.percentile(np.abs(S3 - S1).max(axis=2)[~cur], 95))
    d1 = float(np.abs(S3 - S1).max(axis=2)[cur].mean())
    d2 = float(np.abs(S3 - S2).max(axis=2)[cur].mean())
    print(f"   S3 re-entered: off-cursor p95 {same_p95:.1f}; in-cursor "
          f"|S3-S1| {d1:.1f}, |S3-S2| {d2:.1f}", flush=True)
    if same_p95 > 40:
        results[name] = f"VOID: re-entry is not the same screen (off-cursor p95 {same_p95:.0f})"
    elif d2 < d1 * 0.5:
        results[name] = f"PERSISTS  (in-cursor {d2:.1f} from where left vs {d1:.1f} from opened)"
    elif d1 < d2 * 0.5:
        results[name] = f"RESETS    (in-cursor {d1:.1f} from opened vs {d2:.1f} from where left)"
    else:
        results[name] = f"UNDECIDED (in-cursor {d1:.1f} / {d2:.1f})"
    print(f"   => {results[name]}", flush=True)
    press("B", "5801"); time.sleep(3)

print("\n================ SUMMARY ================")
for k, v in results.items():
    print(f"  {k:12} {v}")
print("SUBMENU FOCUS SWEEP DONE", flush=True)