Join an upload's releases by its par2 set's file names

The files of one upload often became several releases whose names
differ slightly: scene tracks apart from their album's nfo/sfv/par2,
"Vermaechtnis" beside a garbled "Vermächtnis", an index named
Die.Bergretter.S18E05... beside its video wishtv-diebergretter-s18e05.
The par2 merge joined releases only by first-16-KiB hashes, which
readable files never get. A name pass now looks, for every set the
merger finds, at the set poster's releases in its group posted within
12 hours: those whose files the set all names (without case or
punctuation, Latin-1-read UTF-8 read back; sidecars, par2 and images
aside) join the set's release, within the hash pass's file bound.
Merges are kept in release_merges as via 'name'. releases:merge-names
runs it over the sets found before; on 300 recent sets 22 merges of 147
releases, all one upload each.

Also: volumes split after .wmv, .mov, .mpg and other video extensions
share a stem ("Morning Lovers.wmv.001" to ".058" were 58 releases), in
the Rust edge and the TypeScript identity.

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

app/services/par2_merger.ts

@@ -2,7 +2,9 @@ import db from '@adonisjs/lucid/services/db'
 import logger from '@adonisjs/core/services/logger'
 import { par2ReleaseName } from '#lib/release/index'
 import { looksRandom } from '#lib/release/random'
-import { SidecarFolder } from '#services/sidecar_folder'
+import { SidecarFolder, SIDECAR } from '#services/sidecar_folder'
+import { randomPoster } from '#lib/release/identity'
+import NzbService from '#services/nzb_service'
 import { Par2Pruner } from '#services/par2_pruner'
 import { pruneSevenZipTails } from '#services/seven_zip_tails'
 import { decidePar2Completeness } from '#services/par2_completeness'
@@ -23,6 +25,14 @@ const SLACK_FILES = 10
  * ran out of heap every few minutes (LOG.md 2026-10-20 (85)). The judge calls 20 releases repeated.
  */
 const COMMON_FILE = 20
+/**
+ * The name pass: a set's own poster's releases in its group posted this close to it are looked at; at most
+ * NAME_CANDIDATES of them (a poster's uploads of a day).
+ */
+const NAME_SPREAD_MS = 12 * 3600 * 1000
+const NAME_CANDIDATES = 200
+/** Files a set's upload carries besides those it describes: sidecars, its par2 files, a cover or preview. */
+const besideSet = (name: string) => SIDECAR.test(name) || /\.(par2|jpe?g|png)$/i.test(name)
 /** Between rounds. */
 const ROUND_MS = 60_000
 /** A window looks back this far past the previous one's end (rows committed after it was read). */
@@ -45,6 +55,9 @@ export interface MergeRound {
   sets: number
   merges: number
   releases: number
+  /** The name pass: merges, releases in them. */
+  nameMerges: number
+  nameReleases: number
   /** The inner-name pass: stems checked, merges, releases in them. */
   stems: number
   stemMerges: number
@@ -59,6 +72,19 @@ export interface MergeRound {
  */
 const INNER_STEM = `substring(i.result->>'yencName' from '^([A-Za-z0-9]{16,64})\\.')`
 
+/**
+ * A file name as the name pass compares it: without its folder, case, spaces and punctuation, its UTF-8 read back when
+ * it was read as Latin-1 ("Vermächtnis" posted, "Vermächtnis" in the par2).
+ */
+export function fileKey(name: string): string {
+  let n = name.replace(/^.*[\\/]/, '')
+  if (/[\u00c2-\u00f4][\u0080-\u00bf]/.test(n)) {
+    const read = Buffer.from(n, 'latin1').toString('utf8')
+    if (!read.includes('\ufffd')) n = read
+  }
+  return n.normalize('NFC').toLowerCase().replace(/[^\p{L}\p{N}]+/gu, '')
+}
+
 /** The releases holding a par2 file f (its first 16 KiB and size), none when it's a common file (COMMON_FILE). */
 const HOLDERS = `SELECT c.release_id FROM (
     SELECT l.release_id, count(*) OVER () AS holders
@@ -121,6 +147,7 @@ export class Par2Merger {
         }
         const round = await this.round()
         if (round.merges > 0) logger.info(`Merged ${round.releases} releases into ${round.merges} by par2 set (${round.sets} sets checked).`)
+        if (round.nameMerges > 0) logger.info(`Merged ${round.nameReleases} releases into ${round.nameMerges} by their par2 set's file names.`)
         if (round.stemMerges > 0) logger.info(`Merged ${round.stemReleases} releases into ${round.stemMerges} by inner name (${round.stems} stems checked).`)
         if (round.folded?.folded) logger.info(`Folded ${round.folded.folded} sidecars into their uploads (${round.folded.sidecars} sidecar-only of ${round.folded.looked} small releases).`)
       } catch (error: any) {
@@ -155,7 +182,7 @@ export class Par2Merger {
       foldedAt = Date.now()
       if (more.folded) logger.info(`Folded ${more.folded} sidecars into their uploads (${more.sidecars} sidecar-only of ${more.looked} small releases).`)
     }
-    const round: MergeRound = { sets: 0, merges: 0, releases: 0, stems: 0, stemMerges: 0, stemReleases: 0, folded }
+    const round: MergeRound = { sets: 0, merges: 0, releases: 0, nameMerges: 0, nameReleases: 0, stems: 0, stemMerges: 0, stemReleases: 0, folded }
     while (this.since < end) {
       if (this.stopped) return round
       const from = await this.firstNew(new Date(this.since.getTime() - OVERLAP_MS), end)
@@ -176,6 +203,21 @@ export class Par2Merger {
             round.releases += merged + 1
           }
         }
+        // Every set the window found, by its files' names: readable files have no hashes (the files of one upload under
+        // names that differ: scene tracks apart from their album's par2, "Vermaechtnis" beside "Vermächtnis"; LOG.md
+        // 2026-10-23 (97)).
+        const { rows: found } = await db.rawQuery(`SELECT DISTINCT set_id FROM par2_sets WHERE created_at >= ? AND created_at <= ?`, [from, until])
+        for (const { set_id: setId } of found) {
+          if (this.stopped) return round
+          const merged = await this.mergeByName(setId.trim()).catch((error) => {
+            logger.error(`Name merge of set ${setId.trim()} failed: ${error.message}`)
+            return 0
+          })
+          if (merged > 0) {
+            round.nameMerges++
+            round.nameReleases += merged + 1
+          }
+        }
         const { rows: stems } = await db.rawQuery(
           `SELECT DISTINCT ${INNER_STEM} AS stem FROM release_inspections i
            WHERE i.kind = 'lone' AND i.created_at >= ? AND i.created_at <= ? AND ${INNER_STEM} IS NOT NULL`,
@@ -245,6 +287,55 @@ export class Par2Merger {
     return { touched: Number(rows[0].touched), sets: rows[0].sets }
   }
 
+  /**
+   * The releases a set's file names find (mergeByName without merging): its holders, and the releases of the set's
+   * poster in its group posted within NAME_SPREAD_MS whose files the set all names, besides sidecars, par2 and images.
+   * Null when there's nothing to merge.
+   */
+  async nameMatches(trx: any, setId: string): Promise<Map<string, Member> | null> {
+    const { rows: holders } = await trx.rawQuery(
+      `SELECT r.id, r.release_key, r.group_id, r.files, r.posted_at, r.readable, r.poster FROM par2_sets s JOIN releases r ON r.id = s.release_id
+       WHERE s.set_id = ? ORDER BY r.id`,
+      [setId]
+    )
+    const anchor: Member | undefined = holders[0]
+    // A random poster (one per file) bounds nothing: those uploads are the hash pass's.
+    if (!anchor?.poster || !anchor.posted_at || randomPoster(anchor.poster)) return null
+    const { rows: described } = await trx.rawQuery(`SELECT name FROM par2_files WHERE set_id = ?`, [setId])
+    if (described.length === 0) return null
+    const names = new Set(described.map((d: { name: string }) => fileKey(d.name)))
+    const at = new Date(anchor.posted_at).getTime()
+    const { rows: candidates } = await trx.rawQuery(
+      `SELECT r.id, r.release_key, r.group_id, r.files, r.posted_at, r.readable, r.poster FROM releases r
+       WHERE left(r.poster, 200) = left(?, 200) AND r.poster = ? AND r.group_id = ? AND r.posted_at BETWEEN ? AND ? AND r.id <> ALL(?)
+         AND r.files <= ?
+       ORDER BY left(r.poster, 200), r.posted_at DESC NULLS LAST, r.id DESC LIMIT ?`,
+      // More files than the set describes, with its sidecars, can't all be named in it.
+      [anchor.poster, anchor.poster, anchor.group_id, new Date(at - NAME_SPREAD_MS), new Date(at + NAME_SPREAD_MS), holders.map((h: Member) => h.id), described.length + SLACK_FILES, NAME_CANDIDATES]
+    )
+    const found = new Map<string, Member>(holders.map((h: Member) => [String(h.id), h]))
+    let files = holders.reduce((n: number, h: Member) => n + Number(h.files), 0)
+    for (const c of candidates) {
+      const own = await NzbService.files(Number(c.id), trx)
+      const content = own.filter((f) => !besideSet(f.name))
+      if (content.length === 0 || !content.every((f) => names.has(fileKey(f.name)))) continue
+      found.set(String(c.id), c)
+      files += Number(c.files)
+    }
+    if (found.size < 2) return null
+    // No more files than the set describes, with its par2 volumes and sidecars (as the hash pass).
+    if (files > MAX_FILES_PER_SET_FILE * names.size + SLACK_FILES) return null
+    return found
+  }
+
+  /** Merges the releases whose files one set names (nameMatches); how many went into another. */
+  async mergeByName(setId: string): Promise<number> {
+    return db.transaction(async (trx) => {
+      const found = await this.nameMatches(trx, setId)
+      return found ? this.merge(trx, found, setId, 'name') : 0
+    })
+  }
+
   /** Merges the releases whose lone files' inner names share a random stem; how many went into another. */
   async mergeStem(stem: string): Promise<number> {
     return db.transaction(async (trx) => {
@@ -319,7 +410,7 @@ export class Par2Merger {
    * Merges the found releases into the one with the most files (named by the par2 set's files when none
    * is readable); how many went into it. Each merge is kept in release_merges, with its set or stem.
    */
-  private async merge(trx: any, found: Map<string, Member>, key: string, via: 'par2' | 'inner' | 'sidecar'): Promise<number> {
+  private async merge(trx: any, found: Map<string, Member>, key: string, via: 'par2' | 'inner' | 'sidecar' | 'name'): Promise<number> {
     {
       // Locked in id order (the batch store and other rounds take the same rows).
       const { rows: locked } = await trx.rawQuery(`SELECT id FROM releases WHERE id = ANY(?) ORDER BY id FOR UPDATE`, [[...found.keys()]])