-- Best Icon Selection
-- Picks the best completed icon for each host and stores its s3_key in hosts.best_icon_s3_key.
--
-- Target: 32x32 source icon (displayed at 16x16 CSS, crisp on 2x Retina).
--
-- Priority:
--   1. Icons ≥32px: prefer smallest first (closest to 32 — a 32x32 beats a 48x48 beats a 180x180)
--   2. Icons <32px: prefer largest first (16x16 beats 8x8)
--   3. Within same size: prefer PNG > ICO > GIF/JPEG/BMP > WebP
--   4. Tiebreaker: smaller file size
--   SVGs excluded (not supported in bundle generation). Icons ≤2x2 excluded (tracking pixels).
--
-- Usage: psql $DATABASE_URL -f pipeline/04_best_icon/select.sql

UPDATE hosts h SET best_icon_s3_key = sub.s3_key
FROM (
  SELECT DISTINCT ON (i.host_id) i.host_id, i.s3_key
  FROM icons i
  WHERE i.scan_state = 'completed'
    AND i.s3_key IS NOT NULL
    AND i.content_type != 'image/svg+xml'
    AND (i.width IS NULL OR i.width > 2)
    AND (i.height IS NULL OR i.height > 2)
  ORDER BY i.host_id,
    -- Tier: ≥32 preferred over <32. NULL dimensions go last.
    CASE
      WHEN LEAST(COALESCE(i.width, 0), COALESCE(i.height, 0)) >= 32 THEN 0
      WHEN COALESCE(i.width, 0) > 0 THEN 1
      ELSE 2
    END,
    -- Within ≥32: smallest first (closest to 32). Within <32: largest first.
    CASE
      WHEN LEAST(COALESCE(i.width, 0), COALESCE(i.height, 0)) >= 32
        THEN GREATEST(COALESCE(i.width, 0), COALESCE(i.height, 0))
      ELSE -GREATEST(COALESCE(i.width, 0), COALESCE(i.height, 0))
    END,
    -- Format preference
    CASE
      WHEN i.content_type = 'image/png' THEN 0
      WHEN i.content_type IN ('image/x-icon', 'image/vnd.microsoft.icon') THEN 1
      WHEN i.content_type IN ('image/gif', 'image/jpeg', 'image/bmp') THEN 2
      WHEN i.content_type = 'image/webp' THEN 3
      ELSE 4
    END,
    i.file_size ASC
) sub
WHERE h.id = sub.host_id;

-- Stats (human-readable)
\echo '--- Best Icon Selection Stats ---'

SELECT
  COUNT(*) FILTER (WHERE best_icon_s3_key IS NOT NULL) AS hosts_with_icon,
  COUNT(*) FILTER (WHERE best_icon_s3_key IS NULL) AS hosts_without_icon,
  COUNT(*) FILTER (WHERE html_title IS NOT NULL) AS hosts_with_title,
  COUNT(*) FILTER (WHERE html_title IS NOT NULL AND best_icon_s3_key IS NULL) AS title_but_no_icon
FROM hosts
WHERE parsed = TRUE;

-- Stats JSON
\! mkdir -p stats
\t on
\a
\o stats/04_best_icon.json
SELECT json_build_object(
  'hosts_with_icon', COUNT(*) FILTER (WHERE best_icon_s3_key IS NOT NULL),
  'hosts_without_icon', COUNT(*) FILTER (WHERE best_icon_s3_key IS NULL),
  'hosts_with_title', COUNT(*) FILTER (WHERE html_title IS NOT NULL),
  'hosts_no_title', COUNT(*) FILTER (WHERE html_title IS NULL),
  'title_but_no_icon', COUNT(*) FILTER (WHERE html_title IS NOT NULL AND best_icon_s3_key IS NULL)
)
FROM hosts
WHERE parsed = TRUE;
\o
\t off
\a
\echo 'Stats written to stats/04_best_icon.json'