#!/usr/bin/env bash
# Full dedup pipeline:
#   1. Layer 1 (deterministic merges)
#   2. Layer 2 (fuzzy trigram with numeric + code-suffix guards)
#   3. DB remap (entity_mentions → canonical entity_pk)
#   4. Re-sync signal_strength + total_mentions
#   5. Re-run text backfill
#
# Run from /Users/guto/ufo. Requires DATABASE_URL set and SSH tunnel open.
set -euo pipefail
cd /Users/guto/ufo

source /Users/guto/ufo/infra/disclosure-stack/.env
export DATABASE_URL="postgres://postgres:${POSTGRES_PASSWORD}@localhost:5433/postgres"

# Ensure tunnel
ss -ltn 2>/dev/null | grep -q 5433 || {
  pkill -f "ssh.*5433:172" 2>/dev/null || true
  sleep 1
  sshpass -p "$VPS_PASSWORD" ssh -o StrictHostKeyChecking=accept-new \
    -p "$VPS_PORT" -fN -L 5433:172.27.0.2:5432 "${VPS_USER}@${VPS_HOST}"
  sleep 2
}

echo "=== [1/5] Layer 1 dedup (deterministic) — already applied; re-running idempotent"
python3 scripts/maintain/49_dedup_aggressive.py 2>&1 | tail -5

echo ""
echo "=== [2/5] Layer 2 dedup (fuzzy trigram) ==="
python3 scripts/maintain/50_dedup_fuzzy_trigram.py 2>&1 | tail -8

echo ""
echo "=== [3/5] Remap entity_mentions in DB ==="
python3 scripts/maintain/51_remap_entity_mentions.py 2>&1 | tail -10

echo ""
echo "=== [4/5] Resync signal_strength ==="
python3 scripts/maintain/42_sync_entity_stats.py --fix-obj-names 2>&1 | tail -10

echo ""
echo "=== [5/5] Re-run text backfill on the new canonical set ==="
python3 scripts/maintain/46_text_backfill_mentions.py 2>&1 | tail -8

echo ""
echo "=== Done. Final entity counts ==="
python3 -c "
from pathlib import Path
p = Path('wiki/entities')
active = sum(1 for f in p.rglob('*.md') if '_archived' not in f.parts)
archived = sum(1 for f in (p / '_archived').rglob('*.md')) if (p / '_archived').exists() else 0
print(f'  active:   {active}')
print(f'  archived: {archived}')
print(f'  total:    {active + archived}')
"