import * as mammoth from 'mammoth'

export type TranscriptionFileType = 'docx' | 'vtt' | 'txt' | 'md'

export interface ParsedTranscription {
  fileName: string
  fileType: TranscriptionFileType
  text: string
  size: number
}

const VTT_HEADER_RE = /^WEBVTT\s/mi
const VTT_TIMING_RE = /^\d{2}:\d{2}:\d{2}\.\d{3}\s*-->\s*\d{2}:\d{2}:\d{2}\.\d{3}/m
const VTT_CUE_RE = /\d{2}:\d{2}:\d{2}\.\d{3}\s*-->\s*\d{2}:\d{2}:\d{2}\.\d{3}/g

function isVTT(text: string): boolean {
  return VTT_HEADER_RE.test(text) || VTT_TIMING_RE.test(text)
}

function parseVtt(raw: string): string {
  return raw
    .replace(VTT_HEADER_RE, '')
    .replace(/Kind:.*\n?/gi, '')
    .replace(/Language:.*\n?/gi, '')
    .split(/\r?\n/)
    .filter(line => {
      const trimmed = line.trim()
      if (!trimmed) return false
      if (/^\d+$/.test(trimmed)) return false
      if (VTT_TIMING_RE.test(trimmed)) return false
      return true
    })
    .join(' ')
    .replace(/\s+/g, ' ')
    .trim()
}

function detectType(fileName: string): TranscriptionFileType {
  const ext = fileName.split('.').pop()?.toLowerCase()
  if (ext === 'docx') return 'docx'
  if (ext === 'vtt') return 'vtt'
  if (ext === 'md') return 'md'
  return 'txt'
}

export async function parseFile(file: File): Promise<ParsedTranscription> {
  const fileName = file.name
  const fileType = detectType(fileName)
  const size = file.size

  console.log(`[Alpha] Parsing file: ${fileName} (${fileType}, ${size} bytes)`)

  let text: string

  if (fileType === 'docx') {
    const arrayBuffer = await file.arrayBuffer()
    const result = await mammoth.extractRawText({ arrayBuffer })
    text = result.value.trim()
  } else {
    const raw = await file.text()
    if (fileType === 'vtt' || isVTT(raw)) {
      text = parseVtt(raw)
    } else {
      text = raw.trim()
    }
  }

  return { fileName, fileType, text, size }
}