#!/bin/bash
set -uo pipefail
BASE=/home/rafa/joomla-migration/mirror-antiguo
RUN=$(cat "$BASE/CURRENT_RUN")
D=$BASE/runs/$RUN
curl -s -H 'Host: antiguo.feadulta.com' 'http://127.0.0.1:8086/_inv/k2ids.php' > "$D/k2-ids.tsv"
echo "items K2 en BD: $(wc -l < "$D/k2-ids.tsv")"

grep -oP '/item/\K\d+' "$D/404-passC.txt" | sort -u > "$D/404-ids.txt"
echo "ids distintos con 404: $(wc -l < "$D/404-ids.txt")"

awk -F'\t' 'NR==FNR{want[$1]=1;next} ($1 in want){print $2"\t"$3}' "$D/404-ids.txt" "$D/k2-ids.tsv" \
  | sort | uniq -c | sed 's/^/  published,trash: /'
echo "ids que no existen en la BD: $(awk -F'\t' 'NR==FNR{have[$1]=1;next} !($1 in have)' "$D/k2-ids.tsv" "$D/404-ids.txt" | wc -l)"

echo
echo "=== los 172 'resto' ==="
grep -vE '/itemlist/user/|/item/|/anterior/' "$D/404-passC.txt" | sed 's#^http://antiguo.feadulta.com/es/##' | cut -d/ -f1 | sort | uniq -c | sort -rn | head -15