Drop garbage uploads early (D42)

Random-named uploads that never get a real name or password were ~90% of
what seeding stores. Two filters:

- before storing (seeding, ingest): random-named uploads of a dropped
  signature (posting tool from the Message-ID, first group) or of a
  release dropped after its probe aren't stored; 2% of a dropped
  signature's releases are still kept and probed. Stored files of dropped
  signatures aren't probed.
- after a probe: a random-named release that is still unnamed, without
  password, names from files or spot, with all its probes done, and
  encrypted, a container or missing its first article, is deleted and
  tombstoned in dropped_releases.

Signatures are learned by gc:scheduler from a sample of probed releases
(signature_probes); garbage:learn --seed fills it from existing files.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

database/migrations/1768620765270_garbage_filter.ts

@@ -0,0 +1,64 @@
+import { BaseSchema } from '@adonisjs/lucid/schema'
+
+/**
+ * Dropping garbage uploads early (CONCEPT.md D42): random-named uploads that
+ * never get a real name or password.
+ * - upload_signatures: per posting tool (from the Message-ID) and first group,
+ *   how many probed random-named releases got a real name; `dropped` ones
+ *   aren't stored any more (GarbageFilter).
+ * - signature_probes: a sample of probed random-named releases, what
+ *   upload_signatures is learned from (the outcome is read from the release
+ *   at learning time, so names that come later count too).
+ * - dropped_releases: releases deleted after their probe, by release_key, so
+ *   seeding and ingest don't add them again.
+ * - is_real_release_name(): a name someone would search for. is_readable_name
+ *   lets spam through (usenetszene net, VTS_01_1.VOB, Nieuwe map, 100 MiB):
+ *   this also wants a year, episode, resolution, codec or language tag, or
+ *   three words (LOG.md 2026-10-08 (5)). No `?` in its regexes: knex takes it
+ *   for a binding (hence {0,1}).
+ */
+export default class extends BaseSchema {
+  async up() {
+    await this.db.rawQuery(`
+      CREATE TABLE IF NOT EXISTS upload_signatures (
+        tool varchar(32) NOT NULL,
+        group_name text NOT NULL,
+        probed integer NOT NULL DEFAULT 0,
+        named integer NOT NULL DEFAULT 0,
+        dropped boolean NOT NULL DEFAULT false,
+        updated_at timestamptz NOT NULL DEFAULT now(),
+        PRIMARY KEY (tool, group_name))`)
+    await this.db.rawQuery(`
+      CREATE TABLE IF NOT EXISTS signature_probes (
+        release_id bigint PRIMARY KEY,
+        tool varchar(32) NOT NULL,
+        group_name text NOT NULL,
+        probed_at timestamptz NOT NULL DEFAULT now())`)
+    await this.db.rawQuery(`CREATE INDEX IF NOT EXISTS signature_probes_probed_at_idx ON signature_probes (probed_at)`)
+    await this.db.rawQuery(`
+      CREATE TABLE IF NOT EXISTS dropped_releases (
+        release_key varchar(40) PRIMARY KEY,
+        reason varchar(16) NOT NULL,
+        dropped_at timestamptz NOT NULL DEFAULT now())`)
+    await this.db.rawQuery(`
+      CREATE OR REPLACE FUNCTION is_real_release_name(name text) RETURNS boolean IMMUTABLE LANGUAGE sql AS $$
+        SELECT name IS NOT NULL AND is_readable_name(name)
+          AND NOT (
+            name ~* '(usenet|video_ts|nieuwe map|new folder|(^|[^a-z0-9])mib([^a-z0-9]|$))'
+            OR name ~* '^(vts_|sample|cd[0-9])'
+            OR name ~ '^\\(.*\\)$'
+            OR name ~ '^[A-Za-z0-9]{8,}$')
+          AND (
+            name ~* '(^|[^a-z0-9])((19|20)[0-9]{2}|(480|576|720|1080|2160)[pi]|dl|nl)([^a-z0-9]|$)'
+            OR name ~* '(s[0-9]{2}e[0-9]{2}|x26[45]|h\\.{0,1}26[45]|hevc|web[- .]{0,1}(dl|rip)|bluray|remux|german|dutch|multi|flac|mp3|epub|pdf|ac3|dts|xxx)'
+            OR (SELECT count(*) FROM regexp_matches(name, '[A-Za-z]{3,}', 'g')) >= 3)
+      $$`)
+  }
+
+  async down() {
+    await this.db.rawQuery(`DROP FUNCTION IF EXISTS is_real_release_name(text)`)
+    await this.db.rawQuery(`DROP TABLE IF EXISTS dropped_releases`)
+    await this.db.rawQuery(`DROP TABLE IF EXISTS signature_probes`)
+    await this.db.rawQuery(`DROP TABLE IF EXISTS upload_signatures`)
+  }
+}

database/schema.ts

@@ -151,6 +151,17 @@ export class DeferredRangeSchema extends BaseModel {
   declare lastArticle: bigint | number
 }
 
+export class DroppedReleaseSchema extends BaseModel {
+  static $columns = ['droppedAt', 'reason', 'releaseKey'] as const
+  $columns = DroppedReleaseSchema.$columns
+  @column.dateTime()
+  declare droppedAt: DateTime
+  @column()
+  declare reason: string
+  @column({ isPrimary: true })
+  declare releaseKey: string
+}
+
 export class FetchRangeSchema extends BaseModel {
   static $columns = ['backfill', 'createdAt', 'endId', 'error', 'groupId', 'id', 'requeues', 'startId', 'status', 'updatedAt'] as const
   $columns = FetchRangeSchema.$columns
@@ -576,6 +587,19 @@ export class SfvEntrySchema extends BaseModel {
   declare releaseId: bigint | number
 }
 
+export class SignatureProbeSchema extends BaseModel {
+  static $columns = ['groupName', 'probedAt', 'releaseId', 'tool'] as const
+  $columns = SignatureProbeSchema.$columns
+  @column()
+  declare groupName: string
+  @column.dateTime()
+  declare probedAt: DateTime
+  @column({ isPrimary: true })
+  declare releaseId: bigint | number
+  @column()
+  declare tool: string
+}
+
 export class SpotSchema extends BaseModel {
   static $columns = ['articleNumber', 'category', 'createdAt', 'description', 'detailsAt', 'error', 'groupName', 'image', 'keyId', 'messageId', 'postedAt', 'poster', 'processedAt', 'releaseId', 'size', 'spotterId', 'status', 'subcats', 'tag', 'title', 'verified', 'website'] as const
   $columns = SpotSchema.$columns
@@ -638,6 +662,23 @@ export class StagedSegmentSchema extends BaseModel {
   declare stagedAt: DateTime
 }
 
+export class UploadSignatureSchema extends BaseModel {
+  static $columns = ['dropped', 'groupName', 'named', 'probed', 'tool', 'updatedAt'] as const
+  $columns = UploadSignatureSchema.$columns
+  @column()
+  declare dropped: boolean
+  @column()
+  declare groupName: string
+  @column()
+  declare named: number
+  @column()
+  declare probed: number
+  @column({ isPrimary: true })
+  declare tool: string
+  @column.dateTime({ autoCreate: true, autoUpdate: true })
+  declare updatedAt: DateTime
+}
+
 export class UserSchema extends BaseModel {
   static $columns = ['createdAt', 'email', 'fullName', 'id', 'password', 'updatedAt'] as const
   $columns = UserSchema.$columns