#!/usr/bin/env python3
"""
combine.py -- build combined.csv from the three per-architecture
correlated CSVs (correlate_doe.py's output), decoding Q48.16 fixed-point
fields to plain floats and jitter_bits' IEEE754 bit pattern to a real
jitter_ns value, since R has no convenient native uint64/bit-punning
story worth using here.

Usage (from this directory, after running correlate_doe.py for each
architecture against ../results-20260912-with-heartbeat-csv/*-doe-raw.log
to produce amd64-correlated.csv / aarch64-correlated.csv /
riscv64-correlated.csv):

    python3 combine.py amd64-correlated.csv aarch64-correlated.csv riscv64-correlated.csv combined.csv
"""
import csv
import struct
import sys

Q48 = 65536.0

def main():
    if len(sys.argv) < 3:
        print("usage: combine.py <in1.csv> [in2.csv ...] <out.csv>", file=sys.stderr)
        sys.exit(1)
    *in_paths, out_path = sys.argv[1:]

    fields = ["arch", "run_id", "id_idx", "id_label", "rep", "tick_number", "elapsed_ns",
              "tick_interval_ns", "hot_word_count", "avg_word_heat", "window_width",
              "actual_window_size", "predicted_label_hits", "jitter_ns", "apic_ticks",
              "time_trust", "variance", "vm_call_depth_max", "hera_heat", "hermes_heat",
              "artemis_heat"]

    out_rows = []
    for path in in_paths:
        arch = path.split("-correlated.csv")[0].split("/")[-1]
        with open(path) as f:
            for row in csv.DictReader(f):
                jitter_bits = int(row["jitter_bits"])
                jitter_ns = struct.unpack('<d', struct.pack('<Q', jitter_bits))[0]
                out = dict(row)
                out["arch"] = arch
                out["avg_word_heat"] = int(row["avg_word_heat_q48"]) / Q48
                out["time_trust"] = int(row["time_trust_q48"]) / Q48
                out["variance"] = int(row["variance_q48"]) / Q48
                out["hera_heat"] = int(row["hera_heat_q48"]) / Q48
                out["hermes_heat"] = int(row["hermes_heat_q48"]) / Q48
                out["artemis_heat"] = int(row["artemis_heat_q48"]) / Q48
                out["jitter_ns"] = jitter_ns
                out_rows.append({k: out[k] for k in fields})

    with open(out_path, "w", newline="") as f:
        w = csv.DictWriter(f, fieldnames=fields)
        w.writeheader()
        w.writerows(out_rows)

    print(f"rows written: {len(out_rows)}")

if __name__ == "__main__":
    main()