db0d0a03f8
Voz clonada por autor (Fray Marcos, Pagola, Sicre, Arregi) en vez de una única voz genérica para todo el TTS. minimax_tts.py resuelve la voz por post_author (AUTHOR_VOICES) y cae a Nico si no hay clon; fea_post_io.php propaga autor/voz; tts_produce.py y sync_audio_to_prod.py (local→prod, workaround glibc rota del servidor) usan la voz correcta en vez de forzar Nico. Incluye fix de trim_after_author_signature: la heurística de "firma final del autor" confundía encabezados litúrgicos iniciales (p.ej. "CORPUS (A)") con la firma, truncando el texto a sintetizar a un par de palabras. Ahora solo cuenta como firma un párrafo con >200 caracteres de contenido real por delante. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
220 lines
8.7 KiB
Python
220 lines
8.7 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
sync_audio_to_prod.py — Sube a PROD los mp3 de TTS ya generados/enlazados en
|
|
local (fea_audio_done=1) y fija el meta fea_audio_url en prod.
|
|
|
|
Prod (134.0.10.170) tiene glibc rota: scp/sftp NO funcionan (connection closed).
|
|
Workaround: subir el binario por stdin de ssh ("cat > ruta"), igual que el resto
|
|
de scripts que tocan ese servidor (ver feadulta-server-glibc-rota.md).
|
|
|
|
Uso:
|
|
python3 sync_audio_to_prod.py --carta 54254 # sincroniza toda la cola de la carta
|
|
python3 sync_audio_to_prod.py --ids 912,919,3001 # ids concretos
|
|
python3 sync_audio_to_prod.py --carta 54254 --dry-run # solo plan, no toca prod
|
|
|
|
Rollback (despublica en prod lo que este script publicó):
|
|
python3 sync_audio_to_prod.py --rollback --carta 54254
|
|
python3 sync_audio_to_prod.py --rollback --ids 912,919
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import json
|
|
import os
|
|
import subprocess
|
|
import time
|
|
from pathlib import Path
|
|
|
|
WP_CONTAINER = os.environ.get("FEA_WP_CONTAINER", "wordpress-web")
|
|
DB_CONTAINER = os.environ.get("FEA_DB_CONTAINER", "wordpress-mysql")
|
|
DB_NAME = os.environ.get("FEA_DB_NAME", "wordpress_db")
|
|
DB_USER = os.environ.get("FEA_DB_USER", "wordpress_user")
|
|
DB_PASS = os.environ.get("FEA_DB_PASS", "wordpress_pass")
|
|
|
|
PROD_HOST = os.environ.get("FEA_PROD_HOST", "feadulta@134.0.10.170")
|
|
PROD_PASS = os.environ.get("FEA_PROD_PASS", "C6c2A!mAl3Wj.BQF")
|
|
PROD_WPLOAD = os.environ.get("FEA_PROD_WPLOAD", "/web/wp-load.php")
|
|
PROD_HELPER = "/tmp/fea_post_io.php"
|
|
PROD_UPLOADS_TTS = "/web/wp-content/uploads/tts"
|
|
|
|
HELPER_SRC = Path(__file__).resolve().parent / "fea_post_io.php"
|
|
LOCAL_TTS_DIR = Path(__file__).resolve().parent.parent / "wordpress/wp-content/uploads/tts"
|
|
|
|
LOG_FILE = Path(os.environ.get(
|
|
"FEA_AUDIO_SYNC_LOG",
|
|
str(Path(__file__).resolve().parent.parent / "logs/feadulta-audio-sync.log"),
|
|
))
|
|
STATE_FILE = Path(os.environ.get(
|
|
"FEA_AUDIO_SYNC_STATE",
|
|
str(Path(__file__).resolve().parent.parent / "logs/feadulta-audio-sync-state.json"),
|
|
))
|
|
|
|
|
|
def log(msg: str) -> None:
|
|
line = f"[{time.strftime('%Y-%m-%d %H:%M:%S')}] {msg}"
|
|
print(line, flush=True)
|
|
LOG_FILE.parent.mkdir(parents=True, exist_ok=True)
|
|
with LOG_FILE.open("a", encoding="utf-8") as f:
|
|
f.write(line + "\n")
|
|
|
|
|
|
def sh(cmd: list[str], *, input_bytes: bytes | None = None, timeout: int = 120) -> str:
|
|
r = subprocess.run(cmd, input=input_bytes, capture_output=True, timeout=timeout)
|
|
if r.returncode != 0:
|
|
raise RuntimeError(f"cmd falló ({r.returncode}): {' '.join(cmd[:4])}…\n{r.stderr.decode(errors='replace')[:400]}")
|
|
return r.stdout.decode(errors="replace")
|
|
|
|
|
|
# ── Local ────────────────────────────────────────────────────────────────────
|
|
def local_meta(post_id: int, key: str) -> str:
|
|
r = subprocess.run(
|
|
["docker", "exec", WP_CONTAINER, "php", "/tmp/fea_post_io.php", "getmeta", str(post_id), key],
|
|
capture_output=True, text=True, timeout=60,
|
|
)
|
|
return r.stdout.strip()
|
|
|
|
|
|
def carta_article_ids(carta_id: int) -> list[int]:
|
|
q = ("SELECT post_id FROM wp_postmeta "
|
|
f"WHERE meta_key='_carta_id' AND meta_value='{carta_id}' ORDER BY post_id;")
|
|
r = subprocess.run(
|
|
["docker", "exec", DB_CONTAINER, "mysql", f"-u{DB_USER}", f"-p{DB_PASS}",
|
|
DB_NAME, "-N", "-e", q],
|
|
capture_output=True, text=True, timeout=60,
|
|
)
|
|
return [int(x) for x in r.stdout.split() if x.isdigit()]
|
|
|
|
|
|
# ── Prod (glibc rota: nada de scp/sftp, todo por ssh + cat) ────────────────────
|
|
def _ssh_text(remote_cmd: str, *, stdin: str | None = None, timeout: int = 120) -> str:
|
|
cmd = ["sshpass", "-p", PROD_PASS, "ssh", "-o", "StrictHostKeyChecking=accept-new",
|
|
"-o", "ConnectTimeout=20", PROD_HOST, remote_cmd]
|
|
r = subprocess.run(cmd, input=stdin, capture_output=True, text=True, timeout=timeout)
|
|
if r.returncode != 0:
|
|
raise RuntimeError(f"ssh falló ({r.returncode}): {remote_cmd[:80]}…\n{r.stderr.strip()[:400]}")
|
|
return r.stdout
|
|
|
|
|
|
def _ssh_upload_bytes(data: bytes, remote_path: str, *, timeout: int = 180) -> None:
|
|
cmd = ["sshpass", "-p", PROD_PASS, "ssh", "-o", "StrictHostKeyChecking=accept-new",
|
|
"-o", "ConnectTimeout=20", PROD_HOST, f"cat > {remote_path}"]
|
|
sh(cmd, input_bytes=data, timeout=timeout)
|
|
|
|
|
|
_prod_helper_ready = False
|
|
|
|
|
|
def prod_helper(subcmd: str, *args: str) -> str:
|
|
global _prod_helper_ready
|
|
if not _prod_helper_ready:
|
|
_ssh_upload_bytes(HELPER_SRC.read_bytes(), PROD_HELPER)
|
|
_prod_helper_ready = True
|
|
inner = f"FEA_WP_LOAD={PROD_WPLOAD} php {PROD_HELPER} {subcmd} " + " ".join(args)
|
|
return _ssh_text(inner, timeout=60)
|
|
|
|
|
|
def prod_upload_mp3(post_id: int) -> None:
|
|
src = LOCAL_TTS_DIR / f"{post_id}.mp3"
|
|
data = src.read_bytes()
|
|
remote_path = f"{PROD_UPLOADS_TTS}/{post_id}.mp3"
|
|
_ssh_upload_bytes(data, remote_path)
|
|
# Verificación de tamaño (glibc rota => sin fiarse ciegamente del rc=0 de ssh)
|
|
remote_size = int(_ssh_text(f"wc -c < {remote_path}").strip())
|
|
if remote_size != len(data):
|
|
raise RuntimeError(f"tamaño no coincide tras subir #{post_id}: local={len(data)} remoto={remote_size}")
|
|
|
|
|
|
def prod_remove_mp3(post_id: int) -> None:
|
|
_ssh_text(f"rm -f {PROD_UPLOADS_TTS}/{post_id}.mp3")
|
|
|
|
|
|
# ── Estado ───────────────────────────────────────────────────────────────────
|
|
def load_state() -> dict:
|
|
if STATE_FILE.exists():
|
|
try:
|
|
return json.loads(STATE_FILE.read_text())
|
|
except json.JSONDecodeError:
|
|
pass
|
|
return {"synced": []}
|
|
|
|
|
|
def save_state(state: dict) -> None:
|
|
STATE_FILE.parent.mkdir(parents=True, exist_ok=True)
|
|
STATE_FILE.write_text(json.dumps(state, ensure_ascii=False, indent=2))
|
|
|
|
|
|
# ── Sync ─────────────────────────────────────────────────────────────────────
|
|
def sync_one(post_id: int, state: dict, *, dry_run: bool) -> str:
|
|
if local_meta(post_id, "fea_audio_done") != "1":
|
|
return "sin-audio-local"
|
|
if not (LOCAL_TTS_DIR / f"{post_id}.mp3").exists():
|
|
return "mp3-local-ausente"
|
|
if dry_run:
|
|
return "PLAN: subiría mp3 + setaudio"
|
|
|
|
voice = local_meta(post_id, "fea_audio_voice") or "NicoFeadulta2026"
|
|
prod_upload_mp3(post_id)
|
|
prod_helper("setaudio", str(post_id), f"/wp-content/uploads/tts/{post_id}.mp3", voice)
|
|
if post_id not in state["synced"]:
|
|
state["synced"].append(post_id)
|
|
save_state(state)
|
|
return "ok"
|
|
|
|
|
|
def rollback_one(post_id: int, state: dict) -> str:
|
|
prod_helper("unsetaudio", str(post_id))
|
|
prod_remove_mp3(post_id)
|
|
if post_id in state["synced"]:
|
|
state["synced"].remove(post_id)
|
|
save_state(state)
|
|
return "ok"
|
|
|
|
|
|
def main() -> int:
|
|
ap = argparse.ArgumentParser(description="Sincroniza audio TTS local→prod (o lo despublica con --rollback).")
|
|
ap.add_argument("--carta", type=int, default=0, help="WP post ID de la carta local; sincroniza toda su cola.")
|
|
ap.add_argument("--ids", default="", help="Lista CSV de post IDs concretos.")
|
|
ap.add_argument("--rollback", action="store_true", help="Despublica en prod en vez de publicar.")
|
|
ap.add_argument("--dry-run", action="store_true", help="Solo muestra el plan; no toca prod.")
|
|
args = ap.parse_args()
|
|
|
|
if args.ids:
|
|
ids = [int(x) for x in args.ids.split(",") if x.strip().isdigit()]
|
|
elif args.carta:
|
|
ids = carta_article_ids(args.carta)
|
|
else:
|
|
ap.error("hace falta --carta o --ids")
|
|
return 2
|
|
|
|
state = load_state()
|
|
mode = "ROLLBACK" if args.rollback else "SYNC"
|
|
log(f"=== INICIO {mode} audio→prod. {len(ids)} posts candidatos: {ids} ===")
|
|
|
|
ok = skip = err = 0
|
|
for pid in ids:
|
|
try:
|
|
if args.rollback:
|
|
if pid not in state["synced"] and not args.ids:
|
|
res = "no-estaba-sincronizado"
|
|
skip += 1
|
|
else:
|
|
res = rollback_one(pid, state)
|
|
ok += 1
|
|
else:
|
|
res = sync_one(pid, state, dry_run=args.dry_run)
|
|
if res == "ok" or res.startswith("PLAN"):
|
|
ok += 1
|
|
else:
|
|
skip += 1
|
|
log(f" #{pid}: {res}")
|
|
except Exception as exc: # noqa: BLE001
|
|
err += 1
|
|
log(f" #{pid}: ERROR {exc}")
|
|
|
|
log(f"=== FIN {mode}. ok={ok} skip={skip} error={err}. Estado: {STATE_FILE} ===")
|
|
return 1 if err else 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|