#!/usr/bin/env python3
"""Every `opt ` name in every RATC bundle on the disc, by extension -- and the
`.tan` frame sequences among them.

Written to close the reach caveat in docs/re/structures/ratc-child-names.md:
60 of 18 002 RATC children carry no `opt ` block of their own. They are not
children. They are the ten frames of the disc's only `.tan` resource, and one
`opt ` block names the whole run.

    python3 tools/re-capture/ratc_opt_name_census.py

Reads $SYLPHEED_DISC/dat/*.pak directly (IPFB TOC + Z1/zlib entries), so it does
not depend on the Rust parser it is checking. Takes a few minutes.
"""

import struct, zlib, glob, os, collections, bisect
from disc import disc_root
MAG = (b"T8aD", b"RATC", b"ttcf", b"\x89PNG")
ext = collections.Counter()
tan_sites = []
opt_total = 0
DISC = disc_root()
for pakpath in sorted(glob.glob(f"{DISC}/dat/*.pak")):
    base = pakpath[:-4]
    pak = open(pakpath, "rb").read()
    if pak[:4] != b"IPFB": continue
    n = struct.unpack_from(">I", pak, 4)[0]
    toc = [struct.unpack_from(">III", pak, 0x10 + 12*i) for i in range(n)]
    segs = sorted(glob.glob(base + ".p[0-9][0-9]"))
    if not segs: continue
    data = b"".join(open(s, "rb").read() for s in segs)
    for ei, (h, off, cs) in enumerate(toc):
        raw = data[off:off+cs]
        try:
            b = zlib.decompress(raw[10:]) if raw[:2] == b"Z1" else raw
        except Exception:
            continue
        if b[:4] != b"RATC": continue
        names = []
        p = b.find(b"opt ")
        while p >= 0:
            ln = struct.unpack_from(">I", b, p+4)[0] if p+8 <= len(b) else 0
            if 0 < ln <= 64 and p+8+ln <= len(b):
                nm = b[p+8:p+8+ln].decode('latin1', 'replace')
                if nm and all(32 < ord(c) < 127 for c in nm):
                    names.append((p, nm)); opt_total += 1
                    ext[os.path.splitext(nm)[1].lower()] += 1
            p = b.find(b"opt ", p+4)
        offs, i = [], 4
        while i + 4 <= len(b):
            if b[i:i+4] in MAG:
                offs.append(i); i += 4
            else: i += 1
        if not names or not offs: continue
        npos = [p for p, _ in names]
        # each child -> index of the nearest preceding opt
        owner = collections.defaultdict(list)
        for k, o in enumerate(offs):
            j = bisect.bisect_left(npos, o) - 1
            if j >= 0: owner[j].append(k)
        for j, (p, nm) in enumerate(names):
            if not nm.lower().endswith(".tan"): continue
            ks = owner.get(j, [])
            if not ks: continue
            sizes = sorted({(offs[k+1] if k+1 < len(offs) else len(b)) - offs[k] for k in ks})
            tan_sites.append((os.path.basename(pakpath), ei, nm, len(ks), sizes))
print(f"`opt ` blocks disc-wide: {opt_total}")
print("\nby extension:")
for e, c in ext.most_common(25):
    print(f"   {e or '(none)':10} x{c}")
print(f"\n.tan resources with >=1 child: {len(tan_sites)}")
seen = collections.Counter()
for t in tan_sites:
    seen[(t[0], t[2], t[3], tuple(t[4]))] += 1
for (pk, nm, fr, sz), c in sorted(seen.items()):
    print(f"   {pk:24} {nm:30} frames={fr:3} sizes={list(sz)}  x{c} bundles")