added select.sql query

pipeline/04_best_icon/select.sql

@@ -0,0 +1,47 @@
+-- Best Icon Selection
+-- Picks the best completed icon for each host and stores its s3_key in hosts.best_icon_s3_key.
+--
+-- Priority:
+--   1. Standard square sizes (64 > 48 > 32 > 16) — ideal for tab display
+--   2. Other square sizes ≤64
+--   3. Non-square sizes ≤64 on both axes
+--   4. Anything larger (downloaded because rel_sizes was undeclared)
+--   5. Among equal priority: prefer PNG/GIF/ICO over WebP over SVG
+--   6. Tiebreaker: smaller file size (less bandwidth in bundles)
+--
+-- 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
+  ORDER BY i.host_id,
+    CASE
+      WHEN i.width = i.height AND i.width IN (64, 48, 32, 16) THEN 0
+      WHEN i.width = i.height AND i.width <= 64 THEN 1
+      WHEN i.width IS NOT NULL AND i.width <= 64 AND i.height IS NOT NULL AND i.height <= 64 THEN 2
+      ELSE 3
+    END,
+    COALESCE(i.width, 0) DESC,
+    CASE
+      WHEN i.content_type IN ('image/png', 'image/gif', 'image/x-icon', 'image/vnd.microsoft.icon') THEN 0
+      WHEN i.content_type = 'image/webp' THEN 1
+      WHEN i.content_type = 'image/svg+xml' THEN 2
+      ELSE 3
+    END,
+    i.file_size ASC
+) sub
+WHERE h.id = sub.host_id;
+
+-- Stats
+\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;