#!/bin/bash
set -uo pipefail
BASE=/home/rafa/joomla-migration/mirror-antiguo
RUN=$(cat "$BASE/CURRENT_RUN")
DIR=$BASE/runs/$RUN
grep -v '?' "$DIR/missing-pages.txt" > "$DIR/missing-pages-sinquery.txt"
M=$DIR/missing-pages-sinquery.txt
echo "sin query: $(wc -l < "$M")"
echo
echo "=== por prefijo (2 segmentos) ==="
sed 's#^http://antiguo.feadulta.com/##' "$M" | cut -d/ -f1,2 | sort | uniq -c | sort -rn | head -25
echo
echo "=== muestra de 30 (fuera de /anterior) ==="
grep -v '/anterior/' "$M" | shuf -n 30