usenet-indexer/lib/nntp/xover_client.ts

import net from 'node:net'
import tls from 'node:tls'
import { deflateSync, unzipSync } from 'node:zlib'

export interface XoverClientOptions {
  host: string
  port: number
  user?: string
  password?: string
  secure?: boolean
  /** Hostname the TLS certificate must match, when connecting through a tunnel (default: host). */
  servername?: string
  /** A reply with no data for this long fails, and the connection with it (inactivity, not duration). */
  timeoutMs?: number
  /** Ask for gzip-compressed overview data (XFEATURE COMPRESS GZIP), when the server has it. */
  compress?: boolean
}

export type Overview = [number, Record<string, string>]

/** The overview fields in RFC 3977 order, named as nntp-js names them (segmentFromHeader reads these). */
const FIELDS = ['subject', 'from', 'date', 'message-id', 'references', ':bytes', ':lines', 'xref']
const TERMINATOR = Buffer.from('\r\n.\r\n')
const DOT_LINE = Buffer.from('.\r\n')

/**
 * A minimal NNTP client for seeding nodes (CONCEPT.md D37): one connection,
 * GROUP and XOVER only, with gzip-compressed overviews. nntp-js can't read
 * those: after "224 … [COMPRESS=GZIP]" the lines come as one zlib stream,
 * followed by a plain "." line; an empty range is a 420 without body.
 * About six times less traffic per header (LOG.md 2026-10-05).
 */
export class XoverClient {
  private chunks: Buffer[] = []
  private length = 0
  private wake?: () => void
  private failure?: Error
  compressed = false

  private constructor(
    private sock: net.Socket,
    private timeoutMs: number
  ) {
    sock.on('data', (chunk: Buffer) => {
      this.chunks.push(chunk)
      this.length += chunk.length
      this.wake?.()
    })
    const fail = (error: Error) => {
      this.failure ??= error
      this.wake?.()
    }
    sock.on('error', fail)
    sock.on('close', () => fail(new Error('NNTP connection closed')))
    sock.on('timeout', () => {
      fail(new Error('NNTP reply timed out'))
      sock.destroy()
    })
  }

  static async connect(options: XoverClientOptions): Promise<XoverClient> {
    const sock = options.secure
      ? tls.connect({ host: options.host, port: options.port, servername: options.servername || options.host })
      : net.connect({ host: options.host, port: options.port })
    const client = new XoverClient(sock, options.timeoutMs ?? 120_000)
    sock.setTimeout(client.timeoutMs)
    try {
      await client.expect(await client.line(), ['200', '201'])
      if (options.user) {
        const reply = await client.command(`AUTHINFO USER ${options.user}`)
        if (reply.startsWith('381')) await client.expect(await client.command(`AUTHINFO PASS ${options.password ?? ''}`), ['281'])
        else await client.expect(reply, ['281'])
      }
      if (options.compress) client.compressed = (await client.command('XFEATURE COMPRESS GZIP')).startsWith('290')
    } catch (error) {
      client.close()
      throw error
    }
    // Idle between commands is fine (a node waiting for the seed API); only replies are timed.
    sock.setTimeout(0)
    return client
  }

  async group(name: string): Promise<{ count: number; low: number; high: number }> {
    return this.timed(() => this.selectGroup(name))
  }

  /** Overviews of articles `from`..`to` in the current group; an empty range gives []. */
  async xover(from: number, to: number): Promise<Overview[]> {
    return this.timed(() => this.overviews(from, to))
  }

  /**
   * Overviews of `from`..`to` as one zlib/gzip stream, as the server sent it when it
   * compresses (plain replies are deflated here): the seed API passes these to nodes
   * without unpacking them (CONCEPT.md D38). `parseOverviews(unzipSync(raw).toString())`.
   */
  async xoverRaw(from: number, to: number): Promise<Buffer> {
    return this.timed(async () => {
      const reply = await this.command(`XOVER ${from}-${to}`)
      if (reply.startsWith('420') || reply.startsWith('423')) return deflateSync(Buffer.alloc(0))
      await this.expect(reply, ['224'])
      return reply.includes('COMPRESS=GZIP') ? (await this.compressedRaw()).raw : deflateSync(Buffer.from(await this.plainBody()))
    })
  }

  /** A reply that stalls for timeoutMs fails the connection; idle time between commands doesn't count. */
  private async timed<T>(exchange: () => Promise<T>): Promise<T> {
    this.sock.setTimeout(this.timeoutMs)
    try {
      return await exchange()
    } finally {
      this.sock.setTimeout(0)
    }
  }

  private async selectGroup(name: string): Promise<{ count: number; low: number; high: number }> {
    const reply = await this.command(`GROUP ${name}`)
    await this.expect(reply, ['211'])
    const [, count, low, high] = reply.split(' ')
    return { count: Number(count), low: Number(low), high: Number(high) }
  }

  private async overviews(from: number, to: number): Promise<Overview[]> {
    const reply = await this.command(`XOVER ${from}-${to}`)
    if (reply.startsWith('420') || reply.startsWith('423')) return []
    await this.expect(reply, ['224'])
    const data = reply.includes('COMPRESS=GZIP') ? await this.compressedBody() : await this.plainBody()
    return parseOverviews(data)
  }

  close() {
    try {
      this.sock.end('QUIT\r\n')
    } catch {
      // already closed
    }
    this.sock.destroy()
  }

  private async command(line: string): Promise<string> {
    this.sock.write(`${line}\r\n`)
    return this.line()
  }

  private async expect(reply: string, codes: string[]) {
    if (!codes.some((code) => reply.startsWith(code))) throw new Error(`NNTP: unexpected reply "${reply}"`)
  }

  private buffer(): Buffer {
    if (this.chunks.length > 1) this.chunks = [Buffer.concat(this.chunks, this.length)]
    return this.chunks[0] ?? Buffer.alloc(0)
  }

  private take(n: number): Buffer {
    const all = this.buffer()
    const out = all.subarray(0, n)
    const rest = all.subarray(n)
    this.chunks = rest.length > 0 ? [rest] : []
    this.length = rest.length
    return out
  }

  private async more() {
    if (this.failure) throw this.failure
    await new Promise<void>((resolve) => (this.wake = resolve))
    this.wake = undefined
    if (this.failure && this.length === 0) throw this.failure
  }

  private async line(): Promise<string> {
    while (true) {
      const at = this.buffer().indexOf('\r\n')
      if (at !== -1) return this.take(at + 2).subarray(0, at).toString('latin1')
      await this.more()
    }
  }

  /** A plain multi-line body, up to "\r\n.\r\n", dot-unstuffed. */
  private async plainBody(): Promise<string> {
    let searched = 0
    while (true) {
      const all = this.buffer()
      // An empty body is just ".\r\n".
      if (all.length >= 3 && searched === 0 && all.subarray(0, 3).equals(DOT_LINE)) {
        this.take(3)
        return ''
      }
      const at = all.indexOf(TERMINATOR, Math.max(0, searched - TERMINATOR.length))
      if (at !== -1) return this.take(at + TERMINATOR.length).subarray(0, at + 2).toString('utf8').replace(/^\.\./gm, '.')
      searched = all.length
      await this.more()
    }
  }

  private async compressedBody(): Promise<string> {
    return (await this.compressedRaw()).text
  }

  /** A zlib/gzip stream followed by a "." line: complete once it ends in ".\r\n" and inflates. */
  private async compressedRaw(): Promise<{ raw: Buffer; text: string }> {
    while (true) {
      const all = this.buffer()
      if (all.length > DOT_LINE.length && all.subarray(all.length - DOT_LINE.length).equals(DOT_LINE)) {
        const raw = all.subarray(0, all.length - DOT_LINE.length)
        try {
          const text = unzipSync(raw).toString('utf8')
          this.take(all.length)
          return { raw: Buffer.from(raw), text }
        } catch {
          // ".\r\n" inside the compressed data: wait for more.
        }
      }
      await this.more()
    }
  }
}

/** Overview lines (tab-separated, after the article number) as nntp-js returns them. */
export function parseOverviews(data: string): Overview[] {
  const out: Overview[] = []
  for (const line of data.split('\r\n')) {
    if (!line) continue
    const [number, ...tokens] = line.split('\t')
    const fields: Record<string, string> = {}
    for (let i = 0; i < FIELDS.length && i < tokens.length; i++) {
      // Full fields after the defaults carry their name: "Xref: host group:number".
      fields[FIELDS[i]] = i >= 7 ? tokens[i].replace(/^[^:\s]+:\s*/, '') : tokens[i]
    }
    out.push([Number.parseInt(number, 10), fields])
  }
  return out
}