#!/usr/bin/env python3
"""Census of the `fpu_cw` field the shim's template hooks record on every call.

Each hook snapshots the x87 control word as it finds it, so a run's trace carries independent
samples of the word from *inside* the turn pipeline -- phase 4 (MoveFleet), phase 6
(ServerSystem::ProcessTurn) and phase 8 (ComputeBudget / ProcessResearch). That is the evidence
that a control word forced at the turn gate actually held for the duration of the turn, rather
than being silently restored partway through (which would produce identical saves and a
completely false "nothing depends on precision" conclusion).

Usage: cw_census.py <shim.trace.jsonl> [...]
"""
import gzip
import json
import sys
from collections import Counter, defaultdict


def _open(path):
    op = gzip.open if path.endswith(".gz") else open
    return op(path, "rt", encoding="utf-8", errors="replace")


def census(path):
    per_hook = defaultdict(Counter)
    first_last = {}
    n = 0
    with _open(path) as f:
        for line in f:
            line = line.strip()
            if not line.startswith("{"):
                continue
            try:
                rec = json.loads(line)
            except json.JSONDecodeError:
                continue
            hook = rec.get("hook")
            if not hook:
                continue
            n += 1
            for arg in rec.get("args", []) or []:
                if arg.get("n") == "fpu_cw":
                    cw = int(arg["v"])
                    per_hook[hook][cw] += 1
                    key = (hook, cw)
                    if key not in first_last:
                        first_last[key] = [rec.get("call_id"), rec.get("call_id")]
                    else:
                        first_last[key][1] = rec.get("call_id")
    return n, per_hook, first_last


def main():
    for path in sys.argv[1:]:
        n, per_hook, first_last = census(path)
        print(f"== {path}  ({n} hook records)")
        total = Counter()
        for hook in sorted(per_hook):
            for cw, count in sorted(per_hook[hook].items()):
                lo, hi = first_last[(hook, cw)]
                total[cw] += count
                print(f"   {hook:<42} cw=0x{cw:04x}  x{count:<5} call_id {lo}..{hi}")
        if not per_hook:
            print("   (no hook recorded an fpu_cw field)")
        else:
            vals = ", ".join(f"0x{cw:04x} x{c}" for cw, c in sorted(total.items()))
            print(f"   ALL SAMPLES: {vals}")
        print()


if __name__ == "__main__":
    main()