"""Cut the two public long-form files into ~6-minute windows that the seat can actually take whole.

The seat's ONNX graph has a hard ceiling of 5,000 encoder frames (pos_emb_max_len 5000 -> a 9,999-wide
relative-position table) = 400 s; anything longer returns HTTP 500. Windows: nominal boundaries every
360 s, each moved to the widest gap between consecutive ground-truth word starts within +-10 s (a pause),
cut at the middle of that gap; every window must be < 395 s. Ground truth per window = the timed GT tokens
whose start time falls inside it (the investigation's gt/<file>.timed.json, unchanged).
Writes data/long/<file>-w<k>.wav and data/long.jsonl {id, file, k, t0, t1, dur, wav, ref_tokens}.
"""
import json
import sys

import numpy as np

OFFSET = float(sys.argv[1]) if len(sys.argv) > 1 else 0.0   # first cut at OFFSET s (second placement)
NAME = sys.argv[2] if len(sys.argv) > 2 else "long"
import soundfile as sf

ROOT = "/tank/spikes/scriberr-slicer"
OUT = "/tank/spikes/parakeet-ab/data"
rows = []
for f in ("wilde", "scotus"):
    tg = json.load(open(f"{ROOT}/gt/{f}.timed.json"))
    tok, tim = tg["tokens"], tg["times"]
    a, sr = sf.read(f"{ROOT}/public/{f}.wav", dtype="float32")
    total = len(a) / sr
    starts = np.asarray(tim, float)
    gaps = [(starts[i + 1] - starts[i], (starts[i] + starts[i + 1]) / 2) for i in range(len(starts) - 1)]
    cuts = [0.0]
    k = 1
    while total - cuts[-1] > 395:
        nominal = cuts[-1] + (OFFSET if (OFFSET and len(cuts) == 1) else 360)
        cand = [(g, m) for g, m in gaps if abs(m - nominal) <= 10]
        cut = max(cand)[1] if cand else nominal
        cuts.append(cut)
        k += 1
    cuts.append(total)
    for k, (t0, t1) in enumerate(zip(cuts, cuts[1:])):
        assert t1 - t0 < 395, (f, k, t1 - t0)
        seg = a[int(t0 * sr):int(t1 * sr)]
        wav = f"{OUT}/{NAME}/{f}-w{k}.wav"
        import os
        os.makedirs(f"{OUT}/{NAME}", exist_ok=True)
        sf.write(wav, seg, sr, subtype="PCM_16")
        ref = [t for t, s in zip(tok, tim) if t0 <= s < t1]
        rows.append(dict(id=f"{f}-w{k}", file=f, k=k, t0=round(t0, 2), t1=round(t1, 2), dur=round(t1 - t0, 2),
                         wav=wav, ref_tokens=ref))
        print(f, k, round(t0, 1), round(t1, 1), "dur", round(t1 - t0, 1), "ref words", len(ref))
with open(f"{OUT}/{NAME}.jsonl", "w") as fo:
    for r in rows:
        fo.write(json.dumps(r) + "\n")