/**
 * What a searchable string of a release is, as release_texts.kind stores it (a smallint; voyager 3, migration 6200).
 * The table holds every string search matches against (the release name too), appended by whoever learns one: the
 * batch store the name, the prober the file names inside an archive, later passes NFO titles, par2 set names,
 * media titles. The numbers never change meaning once written.
 */
export const TEXT_KINDS = {
  /** The release name (releases.name, once more for the one trigram index). */
  name: 1,
  /** A file name inside an archive (the prober's inner names). */
  file: 2,
  /** A title read from an NFO. */
  nfo: 3,
  /** A par2 set's name when it differs from the release name. */
  par2: 4,
  /** A title from a media container's metadata. */
  media: 5,
} as const

export type TextKind = keyof typeof TEXT_KINDS

/** The longest string stored (release_texts.text is a varchar(255)); longer ones are cut, not refused. */
export const TEXT_MAX = 255
/** The most strings one writer appends per release and kind (an archive of two thousand files is not two thousand rows). */
export const TEXTS_PER_KIND = 20

const NAMES = Object.fromEntries(
  Object.entries(TEXT_KINDS).map(([name, code]) => [code, name])
) as Record<number, TextKind>

/** The code of a kind; throws for an unknown one (a typo would write a wrong number for good). */
export function textKindCode(name: string): number {
  const code = TEXT_KINDS[name as TextKind]
  if (code === undefined) throw new Error(`Unknown release text kind "${name}"`)
  return code
}

/** The name of a stored code; "unknown" for one not listed. */
export function textKindName(code: number | string | null | undefined): TextKind | 'unknown' {
  return NAMES[Number(code)] ?? 'unknown'
}

/**
 * The strings a writer appends for one kind: trimmed, cut to TEXT_MAX, empty ones and repeats dropped, the first
 * TEXTS_PER_KIND kept in the order given (the writer puts the most telling first).
 */
export function textsToStore(texts: Iterable<string | null | undefined>): string[] {
  const seen = new Set<string>()
  const out: string[] = []
  for (const raw of texts) {
    const text = (raw ?? '').trim().slice(0, TEXT_MAX)
    if (!text || seen.has(text)) continue
    seen.add(text)
    out.push(text)
    if (out.length === TEXTS_PER_KIND) break
  }
  return out
}