The pending ladder in the prober: unnamed releases probed cheapest first, signatures learned, the named moved into the catalog

pending_ladder.ts claims the oldest waiting pending releases' next target
(par2, archive, lone, 7z-tail in that order) as at least PENDING_SHARE of each
claim; a usable name (the largest named file of a par2 set or a listing, or a
lone file's yEnc name, neither packaging nor random) hands the release to the
namer, no name the next target or the end of the climb; climbs count on
pending_signatures per (tool, group, poster) and (tool, group), and a signature
with 100 climbs and 0.5% named or fewer is dropped: its waiting releases are
discarded without a probe, the rules' sample excepted. pending_namer.ts reads
a named release's articles again from the corpus or by XOVER and writes it to
the catalog under the pending key (source weak-stem, the name as inner name)
with its chunk and candidates. Migration 6400; config PENDING_*.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

lib/probe/index.ts

@@ -1 +1 @@
-export { inspect, innerName, MAX_NAMES, PROBE_VERSION, type Inspection } from './inspect.js'
+export { inspect, innerName, usableName, MAX_NAMES, PROBE_VERSION, type Inspection } from './inspect.js'

lib/probe/inspect.ts

@@ -5,6 +5,7 @@ import { parseRarHeaders } from '#lib/rar/index'
 import { parseSevenZipTail } from '#lib/sevenzip/index'
 import { parseZipStart } from '#lib/zip/index'
 import { sniffContentType, type ContentType } from '#lib/content/index'
+import { fileStem, looksRandom } from '#lib/release/index'
 
 /** What one probed article showed (REBUILD.md, part 6; stored per release and kind). */
 export interface Inspection {
@@ -25,7 +26,10 @@ export interface Inspection {
    */
   hash16k?: string
   /** A par2 body's recovery set: every file it describes (not kept in release_inspections; par2_files). */
-  par2?: { setId: string; files: { fileId: string; hash16k: string; length: number; name: string }[] }
+  par2?: {
+    setId: string
+    files: { fileId: string; hash16k: string; length: number; name: string }[]
+  }
 }
 
 const HASH_BYTES = 16 * 1024
@@ -63,9 +67,16 @@ function largestFirst(items: { name: string; size: number }[]): string[] {
  */
 export function inspect(body: Buffer, kind?: string): Inspection {
   const segment = decodeBody(body)
-  const result: Inspection = { yencName: segment.meta.begin.name.slice(0, MAX_NAME_LENGTH), size: segment.meta.begin.size, type: sniffContentType(segment.data) }
+  const result: Inspection = {
+    yencName: segment.meta.begin.name.slice(0, MAX_NAME_LENGTH),
+    size: segment.meta.begin.size,
+    type: sniffContentType(segment.data),
+  }
   // The file's first 16 KiB, or all of a smaller file.
-  if (segment.offset === 0 && (segment.data.length >= HASH_BYTES || segment.data.length === result.size)) {
+  if (
+    segment.offset === 0 &&
+    (segment.data.length >= HASH_BYTES || segment.data.length === result.size)
+  ) {
     result.hash16k = createHash('md5').update(segment.data.subarray(0, HASH_BYTES)).digest('hex')
   }
   if (isPar2(segment.data)) {
@@ -76,7 +87,12 @@ export function inspect(body: Buffer, kind?: string): Inspection {
       result.names = largestFirst(set.files.map((f) => ({ name: f.name, size: f.length })))
       result.par2 = {
         setId: set.recoverySetId,
-        files: set.files.map((f) => ({ fileId: f.fileId, hash16k: f.md5_16k, length: f.length, name: f.name.slice(0, MAX_NAME_LENGTH) })),
+        files: set.files.map((f) => ({
+          fileId: f.fileId,
+          hash16k: f.md5_16k,
+          length: f.length,
+          name: f.name.slice(0, MAX_NAME_LENGTH),
+        })),
       }
     }
     return result
@@ -99,7 +115,10 @@ export function inspect(body: Buffer, kind?: string): Inspection {
     }
   }
   // 7z keeps its listing at the end: the last segment of the last volume (a 7z-tail), or a small archive whole.
-  if ((kind === '7z-tail' || result.type === '7z') && segment.offset + segment.data.length === result.size) {
+  if (
+    (kind === '7z-tail' || result.type === '7z') &&
+    segment.offset + segment.data.length === result.size
+  ) {
     const listing = parseSevenZipTail(segment.data)
     if (listing) {
       result.entries = listing.files.length
@@ -110,16 +129,43 @@ export function inspect(body: Buffer, kind?: string): Inspection {
   return result
 }
 
+/**
+ * The usable name one probe of an unnamed release found (the pending ladder, REBUILD.md decision f): the largest
+ * named file of a par2 set or an archive's listing, or a lone file's yEnc name, when it isn't packaging and isn't
+ * random itself (an obfuscated upload's par2 names its random volumes; its yEnc name is mostly the random name
+ * again). Null: this probe named nothing, the next target is tried.
+ */
+export function usableName(inspection: Inspection, kind: string): string | null {
+  const usable = (n: string | undefined) => {
+    if (!n) return null
+    const name = n.replace(/^.*[\\/]/, '').slice(0, 255)
+    return name && !PACKAGING.test(name) && !looksRandom(fileStem(name)) ? name : null
+  }
+  const named = (inspection.names ?? []).map(usable).find((n) => n)
+  if (named) return named
+  return kind === 'lone' || !inspection.names?.length ? usable(inspection.yencName) : null
+}
+
 /**
  * A release's best inner name from its inspections (by probe kind): the
  * largest named entry of an archive, else the largest file of a par2 set
  * that isn't packaging, else a lone file's yEnc name. Null when none says
  * more than the release's own name.
  */
-export function innerName(inspections: { kind: string; result: Inspection }[], releaseName = ''): string | null {
+export function innerName(
+  inspections: { kind: string; result: Inspection }[],
+  releaseName = ''
+): string | null {
   const of = (kind: string) => inspections.filter((i) => i.kind === kind).map((i) => i.result)
-  const content = (kind: string) => of(kind).flatMap((i) => i.names ?? []).find((n) => !PACKAGING.test(n))
-  const pick = content('archive') ?? content('7z-tail') ?? content('par2') ?? of('lone').find((i) => i.yencName && !PACKAGING.test(i.yencName))?.yencName
+  const content = (kind: string) =>
+    of(kind)
+      .flatMap((i) => i.names ?? [])
+      .find((n) => !PACKAGING.test(n))
+  const pick =
+    content('archive') ??
+    content('7z-tail') ??
+    content('par2') ??
+    of('lone').find((i) => i.yencName && !PACKAGING.test(i.yencName))?.yencName
   const name = pick?.replace(/^.*[\\/]/, '').slice(0, 255)
   // The release's own name with an extension says nothing new (a random-named file's yEnc name is mostly its random name).
   return name && !name.toLowerCase().startsWith(releaseName.toLowerCase() || '\0') ? name : null