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>

database/migrations/1770000002200_par2_merge.ts

@@ -0,0 +1,60 @@
+import { BaseSchema } from '@adonisjs/lucid/schema'
+
+/**
+ * The par2 merge (REBUILD.md, phase 2; app/services/par2_merger.ts): what the
+ * prober read that ties files to a par2 set, and the merges made from it.
+ * - file_hashes: per probed article that starts a file, the MD5 of its first 16 KiB and the file's size.
+ * - par2_files: per par2 recovery set, every file it describes (FileDesc: the same 16 KiB MD5, length, name).
+ * - par2_sets: which releases hold a par2 file of a set.
+ * - release_merges: releases merged into another, by set.
+ */
+export default class extends BaseSchema {
+  async up() {
+    this.schema.raw(`
+      CREATE TABLE file_hashes (
+        candidate_id bigint PRIMARY KEY,
+        release_id bigint NOT NULL,
+        hash16k char(32) NOT NULL,
+        size bigint NOT NULL,
+        created_at timestamptz NOT NULL DEFAULT now()
+      )`)
+    this.schema.raw(`CREATE INDEX file_hashes_hash_idx ON file_hashes (hash16k)`)
+    this.schema.raw(`CREATE INDEX file_hashes_release_idx ON file_hashes (release_id)`)
+    this.schema.raw(`CREATE INDEX file_hashes_created_idx ON file_hashes (created_at)`)
+    this.schema.raw(`
+      CREATE TABLE par2_files (
+        set_id char(32) NOT NULL,
+        file_id char(32) NOT NULL,
+        hash16k char(32) NOT NULL,
+        length bigint NOT NULL,
+        name text NOT NULL,
+        PRIMARY KEY (set_id, file_id)
+      )`)
+    this.schema.raw(`CREATE INDEX par2_files_hash_idx ON par2_files (hash16k)`)
+    this.schema.raw(`
+      CREATE TABLE par2_sets (
+        set_id char(32) NOT NULL,
+        release_id bigint NOT NULL,
+        files integer NOT NULL,
+        created_at timestamptz NOT NULL DEFAULT now(),
+        PRIMARY KEY (set_id, release_id)
+      )`)
+    this.schema.raw(`CREATE INDEX par2_sets_release_idx ON par2_sets (release_id)`)
+    this.schema.raw(`CREATE INDEX par2_sets_created_idx ON par2_sets (created_at)`)
+    this.schema.raw(`
+      CREATE TABLE release_merges (
+        id bigserial PRIMARY KEY,
+        from_id bigint NOT NULL,
+        from_key varchar(48) NOT NULL,
+        into_id bigint NOT NULL,
+        set_id char(32) NOT NULL,
+        files integer NOT NULL,
+        created_at timestamptz NOT NULL DEFAULT now()
+      )`)
+    this.schema.raw(`CREATE INDEX release_merges_into_idx ON release_merges (into_id)`)
+  }
+
+  async down() {
+    this.schema.raw(`DROP TABLE IF EXISTS file_hashes, par2_files, par2_sets, release_merges`)
+  }
+}