usenet-indexer/lib/release/readable.ts

import { fileStem } from './identity.js'
import { looksRandom } from './random.js'

/**
 * Readable or not: whether a name says what a release is (the catalog's readable flag, the prober's inner names).
 * looksRandom (random.ts) knows the single-token shapes; this reads a name token by token, so separators, spaces
 * and random "extensions" don't hide a scramble (LOG.md (129)).
 */
/**
 * Tokens that don't make a name readable on their own: packaging, volume numbers and the posting tools' fixed
 * words ("Description - Lt5nHjlo3RiuBb3C", "bd5b4a59f3aa87114dcf75c0-addon").
 */
const NOISE =
  /^(addon|samples?|proof|subs?|nfo|part\d+|vol\d+|description|repost|rep|extras?|bonus|cd\d*|dvd\d*|dis[ck]\d*|par2|rar|zip|7z|mkv|mp4|avi|vol)$/i
/** Mixed tokens that are codes, not scrambles: S02E10, 1080p, 10bit, x264, Win10x64, BDRip720p, 3DMark03, v2, 5th. */
const CODE =
  /^([sS]\d{1,2}[eE]\d{1,3}|[xh]26[45]|[A-Za-z]+\d+([a-z]{1,3}|x(64|86))?|\d+[A-Za-z]{1,3}|\d+[A-Za-z]+\d+)$/
/** The NZBSPLIT tools' hash between their markers is no part of the name. */
const NZBSPLIT = /__NZBSPLIT__[0-9a-f]{32}__NZBSPLIT__/i

/** Scene tags write "i" for "I" between capitals (XCiTE, PRESCRiPTiON): read it as a capital there. */
function sceneCase(t: string): string {
  let out = ''
  for (let i = 0; i < t.length; i++) {
    out +=
      t[i] === 'i' && i > 0 && i < t.length - 1 && /[A-Z]/.test(t[i - 1]) && /[A-Z]/.test(t[i + 1])
        ? 'I'
        : t[i]
  }
  return out
}

/**
 * The signals of a scrambled token: letter/digit and lower-to-upper switches; case switches in both directions; lone
 * lowercase letters between capitals ("NtpUgCmS"); an inner run of 2+ capitals with lowercase on both sides
 * ("tBWTuz", "YDoaROv"); the longest consonant run; vowels (a lowercase y too: "McCartney"); runs of one character class.
 */
function signals(t: string) {
  let switches = 0
  let caseSwitches = 0
  let lone = 0
  let consonants = 0
  let maxConsonants = 0
  for (let i = 0; i < t.length; i++) {
    const c = t[i]
    if (/[b-df-hj-np-tv-z]/i.test(c)) maxConsonants = Math.max(maxConsonants, ++consonants)
    else consonants = 0
    if (i === 0) continue
    const a = t[i - 1]
    if (/\d/.test(a) !== /\d/.test(c)) switches++
    else if (/[a-z]/.test(a) && /[A-Z]/.test(c)) switches++
    if ((/[a-z]/.test(a) && /[A-Z]/.test(c)) || (/[A-Z]/.test(a) && /[a-z]/.test(c))) caseSwitches++
    if (
      i < t.length - 1 &&
      /[a-z]/.test(c) &&
      c !== 'i' &&
      /[A-Z]/.test(a) &&
      /[A-Z]/.test(t[i + 1])
    )
      lone++
  }
  const innerUpper = /[a-z][A-Z]{2,}[a-z]/.test(t)
  const vowels = (t.match(/[aeiouAEIOU]|y/g) ?? []).length
  const runs = (t.match(/[a-z]+|[A-Z]+|\d+/g) ?? []).length
  const letters = (t.match(/[A-Za-z]/g) ?? []).length
  const maxLower = Math.max(0, ...(t.match(/[a-z]+/g) ?? []).map((r) => r.length))
  return {
    switches,
    caseSwitches,
    lone,
    innerUpper,
    maxConsonants,
    vowels,
    runs,
    letters,
    maxLower,
  }
}

/**
 * What one alphanumeric token of a name is: a word (letters only, in one case or Capitalized, 3+ long, not a packaging
 * word), a scramble, or neither (digits, codes, CamelCase, short tokens). Kept in step with names.rs token_kind.
 */
export function tokenKind(t: string): 'word' | 'random' | null {
  if (/^\d+$/.test(t) || NOISE.test(t) || CODE.test(t)) return null
  if (/^[A-Za-z]+$/.test(t)) {
    const s = signals(sceneCase(t))
    if (s.caseSwitches === 0 || (s.caseSwitches === 1 && /^[A-Z][a-z]+$/.test(t))) {
      // A base32 consonant soup ("mrrtmzrzmi4dgmrzmyytqmlbztczbx" without its digit) is no word.
      if (t.length >= 10 && s.vowels * 6 < t.length) return 'random'
      return t.length >= 3 ? 'word' : null
    }
    // Mixed case beyond Capitalization: CamelCase (neutral) or a scramble, which has few vowels and short runs.
    if (
      t.length >= 6 &&
      s.caseSwitches >= 2 &&
      (s.innerUpper || (s.vowels * 4 < t.length && (s.runs >= 4 || s.lone >= 1)))
    )
      return 'random'
    return null
  }
  if (t.length >= 8 && /^[0-9a-f]+$/i.test(t) && (t.match(/\d/g)?.length ?? 0) >= 2) return 'random'
  if (/^[A-Z0-9]+$/.test(t)) {
    // 51294P1CUKR2R35X; COD4MW2REMASTERED (4 switches) and BEATLES1964REMASTER (2) stay.
    return t.length >= 12 && signals(t).switches >= 6 ? 'random' : null
  }
  const s = signals(sceneCase(t))
  if (t.length >= 5 && s.switches >= 3) return 'random'
  if (t.length >= 6 && s.switches >= 2 && (s.lone >= 1 || s.innerUpper || s.maxConsonants >= 4))
    return 'random'
  // Few vowels and no lowercase run of 3+ ("Jk5Pud", "RKi9BCg"; not "HDR10Plus").
  if (t.length >= 6 && s.switches >= 2 && s.vowels * 4 < s.letters && s.maxLower <= 2)
    return 'random'
  return null
}

/**
 * A file or release name no one can read: looksRandom's shapes, or more scrambled tokens than words by letter count
 * ("Zx5AjNaK-mh7CFg6Hf8uu", "Description - Lt5nHjlo3RiuBb3C", "PsNdnYiugfZ"; not "Paul McCartney - Band on the Run",
 * "ShesSoWild - Ester Ana 1080p"). Separators and a random "extension" of any length don't hide a scramble, which
 * looksRandom's single-token shapes miss (15% of the readable catalog on 2026-11-02; LOG.md (129)). The readable
 * flag; the drop rules keep looksRandom, which is narrower.
 */
export function isUnreadableName(name: string): boolean {
  const stem = fileStem(name).replace(NZBSPLIT, ' ')
  if (looksRandom(stem)) return true
  let words = 0
  let random = 0
  for (const t of stem.split(/[^A-Za-z0-9]+/)) {
    if (!t) continue
    const kind = tokenKind(t)
    if (kind === 'word') words += t.length
    else if (kind === 'random') random += t.length
  }
  return random > 0 && random > words
}