#!/bin/bash
# Fase 1 - Inventario de URLs generado por el propio router de Joomla (BD local joomla_mirror)
set -euo pipefail
BASE=/home/rafa/joomla-migration/mirror-antiguo
INV=$BASE/inventory
mkdir -p "$INV"
H='Host: antiguo.feadulta.com'
U='http://127.0.0.1:8086/_genurls.php'

for s in menu catcontent content k2; do
  echo "-> $s"
  curl -s --max-time 900 -H "$H" "$U?set=$s" > "$INV/urls-$s.txt"
  wc -l < "$INV/urls-$s.txt"
done

cat "$INV"/urls-menu.txt "$INV"/urls-catcontent.txt "$INV"/urls-content.txt "$INV"/urls-k2.txt \
  | grep -E '^http://antiguo\.feadulta\.com/' \
  | sort -u > "$INV/urls-input.txt"

echo "=== TOTAL unico ==="
wc -l < "$INV/urls-input.txt"
echo "=== reparto por prefijo ==="
sed 's#^http://antiguo.feadulta.com/es/##' "$INV/urls-input.txt" | cut -d/ -f1 | sort | uniq -c | sort -rn | head -30