fix: critical onlhy

Signed-off-by: Umberto Sgueglia <usgueglia@contractor.linuxfoundation.org>

Author: ulemons

services/apps/packages_worker/src/bin/maven-repo-url-backfill.ts

@@ -23,6 +23,7 @@ const DEFAULT_BATCH_SIZE = 5000
 
 const main = async () => {
   const dryRun = process.argv.includes('--dry-run')
+  const criticalOnly = process.argv.includes('--critical-only')
   const rawBatchSize = process.env.MAVEN_REPO_URL_BACKFILL_BATCH_SIZE
   const parsedBatchSize = rawBatchSize === undefined ? DEFAULT_BATCH_SIZE : Number(rawBatchSize)
   if (!Number.isInteger(parsedBatchSize) || parsedBatchSize <= 0) {
@@ -35,7 +36,7 @@ const main = async () => {
   const batchSize = parsedBatchSize
 
   log.info(
-    { dryRun, batchSize },
+    { dryRun, criticalOnly, batchSize },
     'maven repo-url backfill starting (recompute normalizeScmUrl from declared_repository_url, no POM fetch)...',
   )
 
@@ -46,6 +47,7 @@ const main = async () => {
   const totals = await backfillMavenRepositoryUrls(qx, {
     batchSize,
     dryRun,
+    criticalOnly,
     isShuttingDown: () => shuttingDown,
   })
 

services/apps/packages_worker/src/maven/backfillRepositoryUrl.ts

@@ -42,9 +42,14 @@ export type RepoUrlBackfillTotals = {
  */
 export async function backfillMavenRepositoryUrls(
   qx: QueryExecutor,
-  options: { batchSize: number; dryRun: boolean; isShuttingDown: () => boolean },
+  options: {
+    batchSize: number
+    dryRun: boolean
+    criticalOnly: boolean
+    isShuttingDown: () => boolean
+  },
 ): Promise<RepoUrlBackfillTotals> {
-  const { batchSize, dryRun, isShuttingDown } = options
+  const { batchSize, dryRun, criticalOnly, isShuttingDown } = options
   const totals: RepoUrlBackfillTotals = {
     scanned: 0,
     filled: 0,
@@ -62,7 +67,11 @@ export async function backfillMavenRepositoryUrls(
       break
     }
 
-    const rows = await listMavenPackagesForRepoUrlRecompute(qx, { afterId, limit: batchSize })
+    const rows = await listMavenPackagesForRepoUrlRecompute(qx, {
+      afterId,
+      limit: batchSize,
+      criticalOnly,
+    })
     if (rows.length === 0) break
 
     const updates: { id: number; repositoryUrl: string | null }[] = []
@@ -105,7 +114,10 @@ export async function backfillMavenRepositoryUrls(
     }
 
     afterId = rows[rows.length - 1].id
-    log.info({ afterId, changes: updates.length, dryRun, ...totals }, 'Backfill progress')
+    log.info(
+      { afterId, changes: updates.length, dryRun, criticalOnly, ...totals },
+      'Backfill progress',
+    )
   }
 
   return totals

services/libs/data-access-layer/src/osspckgs/packages.ts

@@ -131,10 +131,13 @@ export type MavenRepoUrlRow = {
  * canonical). Rows with neither are skipped — there is nothing to recompute.
  * Used by the repository_url backfill to re-run the normalizer over stored data
  * without re-fetching POMs from the registry.
+ *
+ * `criticalOnly` restricts the scan to is_critical rows (index-backed by the
+ * partial index on is_critical) — used for a fast, consumer-facing first pass.
  */
 export async function listMavenPackagesForRepoUrlRecompute(
   qx: QueryExecutor,
-  options: { afterId: number; limit: number },
+  options: { afterId: number; limit: number; criticalOnly?: boolean },
 ): Promise<MavenRepoUrlRow[]> {
   return qx.select(
     `
@@ -144,6 +147,7 @@ export async function listMavenPackagesForRepoUrlRecompute(
       repository_url          AS "repositoryUrl"
     FROM packages
     WHERE ecosystem = 'maven'
+      ${options.criticalOnly ? 'AND is_critical' : ''}
       AND id > $(afterId)
       AND (declared_repository_url IS NOT NULL OR repository_url IS NOT NULL)
     ORDER BY id ASC