# -*- coding: utf-8 -*-
"""Baut aus echten deutschen Gespraechstranskripten einen Kalibrier-Datensatz
fuer die rkllm-Quantisierung. Laeuft AUF DEM BOARD (python3 + mysql client).

Format laut rkllm-toolkit 1.3.0: [{"input": "...", "target": "..."}, ...]
"""
import json, subprocess, random

SQL = (
    "select id, transcript from recordings "
    "where transcript is not null and char_length(transcript) > 2000 "
    "and deleted_at is null order by id desc limit 24;"
)

out = subprocess.run(
    ['mysql', '-ucallrec', '-pcallrec123', 'callrec', '-N', '-B', '-e', SQL],
    capture_output=True)
rows = out.stdout.decode('utf-8', 'replace').splitlines()

random.seed(29)
samples = []
for row in rows:
    parts = row.split('\t', 1)
    if len(parts) != 2:
        continue
    rid, text = parts
    # mysql -B escapt Zeilenumbrueche als \n
    text = text.replace('\\n', '\n').replace('\\t', '\t')
    text = ' '.join(text.split())
    if len(text) < 2000:
        continue
    # drei Ausschnitte je Aufnahme: Anfang, Mitte, zufaellig
    starts = [0, max(0, len(text) // 2 - 600)]
    if len(text) > 6000:
        starts.append(random.randint(1000, len(text) - 2000))
    for st in starts:
        chunk = text[st:st + 1400].strip()
        if len(chunk) > 800:
            samples.append({"input": chunk, "target": ""})

random.shuffle(samples)
samples = samples[:64]
with open('/tmp/calib-de.json', 'w', encoding='utf-8') as f:
    json.dump(samples, f, ensure_ascii=False, indent=1)

print('Samples: %d' % len(samples))
print('Zeichen gesamt: %d' % sum(len(s['input']) for s in samples))
print('Durchschnitt: %d' % (sum(len(s['input']) for s in samples) // max(1, len(samples))))