use optimized rsid lookups also in variants/phenotypes

Author: ottojolanki

clickhouserewrite.md

@@ -248,3 +248,9 @@ All other routers in `src/routers/datatypeRouters/edges/` and `src/routers/datat
 4. Use three-query pagination for endpoints that merge results from multiple sources
 5. Use lean projections + two-step ID resolution for high-cardinality string lookups on large tables
 6. Use materialized view lookup tables for array column lookups (e.g. `rsid`)
+
+### Important: always use optimized variant lookups
+
+Any endpoint that resolves variant identifiers (`spdi`, `hgvs`, `ca_id`, `rsid`) to variant IDs **must** use the optimized lookup paths — lean projections for `spdi`/`hgvs`/`ca_id` and the `rsid_to_variant` materialized view for `rsid`. Never query the `variants` table directly with `WHERE spdi = ...`, `WHERE hgvs = ...`, or `WHERE has(rsid, ...)` when selecting full rows or when used as a subquery without the lean projection.
+
+This applies to both direct variant queries (`/variants`) and any edge endpoint that accepts variant identifiers as input (e.g. `/variants/phenotypes`, `/variants/genes`, etc.). The `variantIDSearch()` and `findVariantIDByRSID()` functions in `variants.ts` already use the optimized paths and should be reused by all edge routers that resolve variant identifiers. Bypassing these functions with direct `has(rsid, ...)` or unaliased `WHERE spdi = ...` queries against the 1.2B-row `variants` table will result in 60s+ timeouts.

src/routers/datatypeRouters/nodes/variants.ts

@@ -614,6 +614,24 @@ export async function variantIDSearch (input: paramsFormatType): Promise<any[]>
     }
   }
 
+  // Fast path: resolve rsid via lookup table, spdi/ca_id/hgvs via lean projections
+  if (input.rsid !== undefined) {
+    const rows = await chQuery<{ variant_id: string }>(
+      'SELECT variant_id FROM rsid_to_variant WHERE rsid = {_rsid:String}',
+      { _rsid: input.rsid as string }
+    )
+    return rows.map(r => r.variant_id)
+  }
+  for (const col of LEAN_LOOKUP_COLS) {
+    if (input[col] !== undefined) {
+      const rows = await chQuery<{ id: string }>(
+        `SELECT id FROM ${TABLE} WHERE ${col} = {_lp_val:String}`,
+        { _lp_val: input[col] as string }
+      )
+      return rows.map(r => r.id)
+    }
+  }
+
   const params: QueryParams = {}
   const where = buildVariantWhere(input, params)
   if (where === '') return []