The par2 merge: releases whose files one par2 set describes become one

The prober stores, per probed article that starts a file, the MD5 of its
first 16 KiB (file_hashes), and per par2 body the set's whole file list
(par2_files, par2_sets): FileDesc holds the same hash per file, whatever
the file was renamed to. releases:merge (the merger service, no NNTP)
merges every minute the releases of one group, posted within 48 hours of
a release holding the set's par2, whose files the set describes, into the
one with the most files: chunks, probe candidates, inspections, hashes and
counts move; the par2's shared name when none was readable; release_merges
keeps what went where. Obfuscated uploads whose files were each a release
of their own ("[9/20] - "14f5999a…"", hep: 13,232) become one.

Also: corpus_sweep.py counts the marked ranges without psql's command tag.

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

app/services/prober.ts

@@ -159,8 +159,10 @@ export class Prober {
         `INSERT INTO release_inspections (release_id, candidate_id, kind, result)
          SELECT v.release_id, v.candidate_id, v.kind, v.result FROM jsonb_to_recordset(?::jsonb) AS v(release_id bigint, candidate_id bigint, kind text, result jsonb)
          ON CONFLICT (release_id, candidate_id) DO UPDATE SET result = excluded.result, created_at = now()`,
-        [JSON.stringify(done.map((o) => ({ release_id: o.candidate.releaseId, candidate_id: o.candidate.id, kind: o.candidate.kind, result: o.inspection })))]
+        // A par2 set's file list goes to par2_files, not into every inspection.
+        [JSON.stringify(done.map((o) => ({ release_id: o.candidate.releaseId, candidate_id: o.candidate.id, kind: o.candidate.kind, result: { ...o.inspection, par2: undefined } })))]
       )
+      await this.storeForMerge(trx, done)
       // Each touched release from all its inspections (earlier rounds may have stored others).
       const ids = [...new Set(done.map((o) => o.candidate.releaseId))]
       const { rows } = await trx.rawQuery(
@@ -187,6 +189,30 @@ export class Prober {
     })
   }
 
+  /** What the par2 merge matches (app/services/par2_merger.ts): files' first-16-KiB hashes, par2 sets' file lists. */
+  private async storeForMerge(trx: any, done: Outcome[]) {
+    const hashed = done.filter((o) => o.inspection!.hash16k)
+    if (hashed.length > 0) {
+      await trx.rawQuery(
+        `INSERT INTO file_hashes (candidate_id, release_id, hash16k, size)
+         SELECT v.candidate_id, v.release_id, v.hash16k, v.size FROM jsonb_to_recordset(?::jsonb) AS v(candidate_id bigint, release_id bigint, hash16k text, size bigint)
+         ON CONFLICT (candidate_id) DO NOTHING`,
+        [JSON.stringify(hashed.map((o) => ({ candidate_id: o.candidate.id, release_id: o.candidate.releaseId, hash16k: o.inspection!.hash16k, size: o.inspection!.size })))]
+      )
+    }
+    for (const o of done) {
+      const set = o.inspection!.par2
+      if (!set) continue
+      await trx.rawQuery(
+        `INSERT INTO par2_files (set_id, file_id, hash16k, length, name)
+         SELECT ?, v.file_id, v.hash16k, v.length, v.name FROM jsonb_to_recordset(?::jsonb) AS v(file_id text, hash16k text, length bigint, name text)
+         ON CONFLICT DO NOTHING`,
+        [set.setId, JSON.stringify(set.files.map((f) => ({ file_id: f.fileId, hash16k: f.hash16k, length: f.length, name: f.name })))]
+      )
+      await trx.rawQuery(`INSERT INTO par2_sets (set_id, release_id, files) VALUES (?, ?, ?) ON CONFLICT DO NOTHING`, [set.setId, o.candidate.releaseId, set.files.length])
+    }
+  }
+
   private report() {
     const seconds = (Date.now() - this.stats.since) / 1000
     if (seconds < REPORT_MS / 1000) return