#!/bin/bash
# Preparacion del crawl: hosts, liberacion de RAM, estructura de la corrida
set -uo pipefail
BASE=/home/rafa/joomla-migration/mirror-antiguo
INV=$BASE/inventory
WORKERS=${WORKERS:-4}

IP=$(docker inspect joomla-mirror-web -f '{{range $k,$v := .NetworkSettings.Networks}}{{$v.IPAddress}}{{end}}')
if ! grep -q 'antiguo.feadulta.com' /etc/hosts; then
  echo "$IP antiguo.feadulta.com" | sudo -n tee -a /etc/hosts >/dev/null 2>&1 \
    || echo "AVISO: no pude escribir /etc/hosts (hazlo como root)"
fi
grep 'antiguo.feadulta.com' /etc/hosts || true

# --- parar contenedores no implicados (autorizado por Rafa) ---
KEEP='joomla-mirror-web|joomla-mysql|gitea|hub-proxy|beszel-agent'
STOPPED=$BASE/stopped-containers.txt
if [ ! -s "$STOPPED" ]; then
  docker ps --format '{{.Names}}' | grep -vE "^($KEEP)$" > "$STOPPED"
  echo "--- parando ---"; cat "$STOPPED"
  xargs -r -a "$STOPPED" docker stop >/dev/null
fi
echo "--- en marcha ahora ---"
docker ps --format '{{.Names}}' | tr '\n' ' '; echo

# --- estructura de la corrida ---
RUN=$(date -u +%Y%m%dT%H%M%SZ)
DIR=$BASE/runs/$RUN
mkdir -p "$DIR/raw" "$DIR/chunks" "$DIR/logs"
echo "$RUN" > "$BASE/CURRENT_RUN"

split -n l/$WORKERS -d --additional-suffix=.txt "$INV/urls-input.txt" "$DIR/chunks/urls-"
wc -l "$DIR/chunks"/*.txt

cat > "$DIR/meta.json" <<EOF
{
  "run": "$RUN",
  "origen": "Joomla legacy restaurado en local (contenedor joomla-mirror-web, BD joomla_mirror)",
  "origen_ip": "$IP",
  "host_virtual": "antiguo.feadulta.com",
  "inventario": "inventory/urls-input.txt",
  "urls_inventario": $(wc -l < "$INV/urls-input.txt"),
  "workers": $WORKERS,
  "wget": "$(wget --version | head -1)",
  "nota": "Crawl acotado por inventario de BD. Sin recursion. Ver issue rafa/feadulta#180 comment-499."
}
EOF
cat "$DIR/meta.json"
free -g | head -2