#!/usr/bin/env python3
"""Verify the craft -> roster link at roster_base + 0x08.

The delta histogram showed exactly 300 pointers at +0x08 with 300 craft present,
every other delta appearing at most twice. That is a candidate 1:1 link. Before
believing it, this checks the thing a coincidence cannot survive: the craft's own
unit type (from its definition pointer) must equal the unit type of the roster
record it points at (resolved independently via that record's +0x04 name chain).
"""
import os, sys, struct, collections, bisect
sys.path.insert(0, __file__.rsplit('/', 1)[0])
import gmem, gworld, entities2
import importlib.util
_w3 = importlib.util.spec_from_file_location('w3', __file__.rsplit('/', 1)[0] + '/wave3_probe.py')
wave3 = importlib.util.module_from_spec(_w3); _w3.loader.exec_module(wave3)

ROSTER_VT = struct.pack('>I', 0x820AF030)
DELTA, WIN, LINK = 0x130, 0x400, 0x08

def scan_vt(fd, size, vt):
    out = []
    for a, b in gmem.extents(fd, size):
        pos = a
        while pos < b:
            n = min(1 << 24, b - pos)
            blob = os.pread(fd, n, pos)
            i = blob.find(vt)
            while i != -1:
                if (pos + i) % 4 == 0: out.append(pos + i)
                i = blob.find(vt, i + 1)
            pos += n
    return sorted(out)

def main():
    w = gworld.World(); fd = w.fd
    defs = entities2.definitions(w)
    if not defs: print('NOT IN A MISSION'); return 2
    roster = scan_vt(fd, w.size, ROSTER_VT)
    f = os.fdopen(os.dup(fd), 'rb')
    rec = {}                       # roster VA -> (offset, unit id)
    for o in roster:
        va = gmem.primary_va(o)
        if va is None: continue
        rec[va] = (o, wave3.resolve_id(f, w.size, o)[0] or '?')
    print('roster records: %d (labelled %d)'
          % (len(rec), sum(1 for _, n in rec.values() if n != '?')))

    lo, hi = gmem.va_to_off(entities2.ENT_VA_LO), gmem.va_to_off(entities2.ENT_VA_HI)
    craft, pos = [], lo
    while pos < hi:
        n = min(1 << 24, hi - pos)
        blob = os.pread(fd, n, pos)
        for k in range(0, len(blob) - 3, 4):
            nm = defs.get(blob[k:k+4])
            if nm: craft.append((pos + k - DELTA, nm))
        pos += n
    print('live craft: %d' % len(craft))

    want = {va + LINK: va for va in rec}
    fan = collections.Counter(); agree = disagree = nolink = multi = 0
    per_record = collections.Counter(); mismatches = []
    for off, nm in craft:
        blob = os.pread(fd, WIN, off)
        tgt = []
        for k in range(0, len(blob) - 3, 4):
            (p,) = struct.unpack_from('>I', blob, k)
            if p in want: tgt.append((k, want[p]))
        fan[len(tgt)] += 1
        if not tgt: nolink += 1; continue
        if len(tgt) > 1: multi += 1
        rva = tgt[0][1]; per_record[rva] += 1
        rn = rec[rva][1]
        if rn == nm: agree += 1
        else:
            disagree += 1
            if len(mismatches) < 6: mismatches.append((nm, rn))
    print('\n--- link at roster_base + %#x ---' % LINK)
    print('  craft fan-out histogram:', sorted(fan.items()))
    print('  craft with no link: %d   with >1: %d' % (nolink, multi))
    print('  UNIT TYPE AGREES: %d    disagrees: %d' % (agree, disagree))
    if mismatches: print('  sample mismatches (craft vs record):', mismatches)
    print('  pointer offsets used:',
          collections.Counter(k for off, nm in craft[:0] for k in []).most_common())
    print('\n--- craft per roster record ---')
    print('  records referenced: %d / %d' % (len(per_record), len(rec)))
    print('  fan-in histogram:', sorted(collections.Counter(per_record.values()).items()))
    top = sorted(per_record.items(), key=lambda kv: -kv[1])[:6]
    for va, c in top:
        print('    %#010x  %-32s x%d' % (va, rec[va][1], c))
    return 0

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