#!/usr/bin/env bash
# validate-cohort.sh — sanity-check a soft-launch beta cohort CSV
# before it gets fed to send-invitations.sh.
#
# The CSV is the operator's curated list of beta-tester emails +
# segmentation. This script catches the avoidable mistakes BEFORE
# we batch-insert 100 rows into beta_invites and start spraying
# emails :
#
#   - Empty file or wrong header
#   - Duplicate emails (would create 2 invites for the same person)
#   - Malformed emails (missing @, leading/trailing whitespace)
#   - Cohort distribution looks off (no creators, only one segment,
#     under-50 total — soft-launch acceptance gate is ≥50 testers)
#   - Email collisions with existing users (already registered = the
#     invite code is wasted)
#
# v1.0.10 Cluster 3.4.
#
# Usage :
#   bash scripts/soft-launch/validate-cohort.sh path/to/cohort.csv
#
# Optional env :
#   DATABASE_URL  if set, also checks for collisions with the users
#                 table (email already registered → flagged but not
#                 fatal — operator may want to invite an existing
#                 user back to test the new flows).
#   MIN_COHORT    minimum total rows required (default 50, matches the
#                 acceptance-gate threshold in SOFT_LAUNCH_BETA_2026.md).
#   MIN_CREATORS  minimum number of creator-* cohort rows (default 5).
#
# Exit codes :
#   0  — cohort valid
#   1  — cohort malformed (will block send-invitations.sh)
#   2  — cohort merely warns (size below minimum, missing collision
#                              check) ; operator may proceed with --force
set -euo pipefail

CSV=${1:-}
if [ -z "$CSV" ] || [ ! -f "$CSV" ]; then
  cat >&2 <<EOF
usage : bash scripts/soft-launch/validate-cohort.sh path/to/cohort.csv

CSV format (header required) :
  email,cohort,sent_by_email
  alice@example.com,creator-vinyl,ops@veza.fr
  bob@example.com,listener-jazz,ops@veza.fr
  ...

cohort labels are free-text but should follow the convention
<role>-<segment> so the post-launch attribution report groups cleanly.
EOF
  exit 1
fi

MIN_COHORT=${MIN_COHORT:-50}
MIN_CREATORS=${MIN_CREATORS:-5}

# 1. Header check.
header=$(head -1 "$CSV" | tr -d '\r')
if [ "$header" != "email,cohort,sent_by_email" ]; then
  echo "ERROR: header line must be exactly 'email,cohort,sent_by_email' (got: $header)" >&2
  exit 1
fi

# 2. Row count + duplicates + email shape (awk pipeline reads once).
total=0
malformed=0
duplicates=0
declare -A seen
declare -A cohort_count
declare -a malformed_lines

while IFS=, read -r email cohort sent_by_email; do
  email=$(echo "$email" | tr -d '\r' | xargs)
  cohort=$(echo "$cohort" | tr -d '\r' | xargs)

  total=$(( total + 1 ))

  # Email shape : must contain exactly one @, no whitespace, > 5 chars.
  if [[ ! "$email" =~ ^[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}$ ]]; then
    malformed=$(( malformed + 1 ))
    malformed_lines+=("  line $(( total + 1 )) : invalid email '$email'")
    continue
  fi

  # Duplicate detection.
  if [ -n "${seen[$email]:-}" ]; then
    duplicates=$(( duplicates + 1 ))
    malformed_lines+=("  line $(( total + 1 )) : duplicate email '$email' (first seen at line ${seen[$email]})")
    continue
  fi
  seen[$email]=$(( total + 1 ))

  # Cohort tally.
  cohort_count[$cohort]=$(( ${cohort_count[$cohort]:-0} + 1 ))
done < <(tail -n +2 "$CSV")

echo "----------------------------------------------------------------"
echo "Cohort validation report"
echo "----------------------------------------------------------------"
echo "  CSV file       : $CSV"
echo "  Total rows     : $total"
echo "  Unique emails  : ${#seen[@]}"
echo "  Malformed rows : $malformed"
echo "  Duplicates     : $duplicates"
echo ""
echo "Distribution by cohort :"
for c in "${!cohort_count[@]}"; do
  printf "  %-40s %d\n" "$c" "${cohort_count[$c]}"
done | sort
echo ""

exit_code=0

# 3. Hard checks (block send).
if [ "$malformed" -gt 0 ] || [ "$duplicates" -gt 0 ]; then
  echo "ERROR: $malformed malformed + $duplicates duplicate row(s) — fix before sending."
  for line in "${malformed_lines[@]}"; do
    echo "$line"
  done
  exit 1
fi

# 4. Soft checks (warn, don't block — operator decides).
if [ "$total" -lt "$MIN_COHORT" ]; then
  echo "WARN : cohort has $total rows ; soft-launch acceptance gate is ≥ $MIN_COHORT."
  exit_code=2
fi

creator_total=0
for c in "${!cohort_count[@]}"; do
  if [[ "$c" == creator-* ]]; then
    creator_total=$(( creator_total + cohort_count[$c] ))
  fi
done
if [ "$creator_total" -lt "$MIN_CREATORS" ]; then
  echo "WARN : only $creator_total creator-* cohort rows ; goal is ≥ $MIN_CREATORS for upload-flow coverage."
  exit_code=2
fi

if [ "${#cohort_count[@]}" -lt 3 ]; then
  echo "WARN : only ${#cohort_count[@]} distinct cohort labels — feedback will be narrow."
  exit_code=2
fi

# 5. Optional : DATABASE_URL collision check.
if [ -n "${DATABASE_URL:-}" ]; then
  command -v psql >/dev/null 2>&1 || {
    echo "WARN : DATABASE_URL set but psql not on \$PATH ; skipping collision check."
    exit_code=2
  }
  if command -v psql >/dev/null 2>&1; then
    emails_csv=$(printf '%s,' "${!seen[@]}" | sed 's/,$//')
    collisions=$(psql "$DATABASE_URL" -A -t -c "
      SELECT count(*) FROM users WHERE email = ANY(string_to_array('$emails_csv', ','));
    " 2>/dev/null | tr -d ' ' || echo "?")
    if [ "$collisions" = "?" ]; then
      echo "WARN : couldn't query users table (psql connection issue) ; skipping collision check."
      exit_code=2
    elif [ "$collisions" -gt 0 ]; then
      echo "INFO : $collisions email(s) in the cohort already exist in the users table — invite codes will be wasted on existing accounts."
      exit_code=2
    fi
  fi
fi

echo ""
case $exit_code in
  0) echo "PASS : cohort valid, ready for send-invitations.sh." ;;
  2) echo "WARN : cohort valid but with caveats — review and re-run with --force from send-invitations.sh if intentional." ;;
esac
exit $exit_code