llm-in-text/src/utils/docBlock.js

export const DOC_BLOCK_NODE_TYPE = 'doc_block'
export const DOC_BLOCK_FENCE_LANG = 'llm-file'
export const DOC_CONTEXT_LIMIT = 32 * 1024

const IMAGE_MD_RE = /!\[[^\]]*]\([^)]+\)/g
const IMAGE_HTML_RE = /<img\b[^>]*>/gi
const HEADER_SEPARATOR = '\n---\n'
const FENCED_DOC_BLOCK_RE = /(^|\n)(`{3,})llm-file[^\n]*\n([\s\S]*?)\n\2(?=\n|$)/g
const LEGACY_DOC_BLOCK_RE = /<doc_type="[^"]+"\s+doc_name="[^"]+"\s+upload_time="[^"]+"(?:\s+collapsed="[^"]+")?>[\s\S]*?<\/doc_end>/g

function normalizeMarkdownText(markdown = '') {
  return String(markdown || '').replace(/\r\n?/g, '\n')
}

function clipDocContext(content = '', limit = 0) {
  if (!limit || content.length <= limit) return content
  return `${content.slice(0, limit)}...`
}

const AUDIO_EXT_RE = /\.(wav|mp3|m4a|ogg|flac)$/i
const VIDEO_EXT_RE = /\.(mp4|webm|mov|avi|mkv|m4v|ogv)$/i

export function normalizeDocType(value = '') {
  const lower = String(value || '').trim().toLowerCase()
  if (lower === 'txt' || lower === 'text' || lower === 'plain') return 'txt'
  if (lower === 'json') return 'json'
  if (lower === 'toml') return 'toml'
  if (lower === 'yaml' || lower === 'yml') return 'yaml'
  if (lower === 'doc' || lower === 'docx' || lower === 'word') return 'docx'
  if (lower === 'ppt' || lower === 'pptx' || lower === 'powerpoint') return 'pptx'
  if (lower === 'pdf') return 'pdf'
  // Audio types - map to their extensions for doc block display
  if (lower === 'wav' || lower === 'wave') return 'wav'
  if (lower === 'mp3' || lower === 'mpeg') return 'mp3'
  if (lower === 'm4a' || lower === 'aac') return 'm4a'
  if (lower === 'ogg' || lower === 'opus') return 'ogg'
  if (lower === 'flac') return 'flac'
  return 'txt'
}

export function getDocTypeFromFilename(name = '') {
  const lower = String(name || '').toLowerCase()
  if (lower.endsWith('.docx')) return 'docx'
  if (lower.endsWith('.pptx')) return 'pptx'
  if (lower.endsWith('.pdf')) return 'pdf'
  if (lower.endsWith('.json')) return 'json'
  if (lower.endsWith('.toml')) return 'toml'
  if (lower.endsWith('.yaml') || lower.endsWith('.yml')) return 'yaml'
  // Audio types - preserve the actual extension for display
  if (lower.endsWith('.wav')) return 'wav'
  if (lower.endsWith('.mp3') || lower.endsWith('.mpeg')) return 'mp3'
  if (lower.endsWith('.m4a') || lower.endsWith('.aac')) return 'm4a'
  if (lower.endsWith('.ogg') || lower.endsWith('.opus')) return 'ogg'
  if (lower.endsWith('.flac')) return 'flac'
  return 'txt'
}

export function isAudioFile(file) {
  if (!file) return false
  const name = String(file.name || '').toLowerCase()
  const type = String(file.type || '').toLowerCase()
  return AUDIO_EXT_RE.test(name) || type.startsWith('audio/')
}

export function isVideoFile(file) {
  if (!file) return false
  const name = String(file.name || '').toLowerCase()
  const type = String(file.type || '').toLowerCase()
  return VIDEO_EXT_RE.test(name) || type.startsWith('video/')
}

export function isSupportedDocFile(file) {
  if (!file) return false
  const name = String(file.name || '').toLowerCase()
  const type = String(file.type || '').toLowerCase()
  return (
    name.endsWith('.txt') ||
    name.endsWith('.json') ||
    name.endsWith('.toml') ||
    name.endsWith('.yaml') ||
    name.endsWith('.yml') ||
    name.endsWith('.docx') ||
    name.endsWith('.pptx') ||
    name.endsWith('.pdf') ||
    AUDIO_EXT_RE.test(name) ||
    VIDEO_EXT_RE.test(name) ||
    type === 'text/plain' ||
    type === 'application/json' ||
    type === 'text/yaml' ||
    type === 'text/x-yaml' ||
    type === 'application/x-yaml' ||
    type === 'application/vnd.openxmlformats-officedocument.wordprocessingml.document' ||
    type === 'application/vnd.openxmlformats-officedocument.presentationml.presentation' ||
    type === 'application/pdf' ||
    type.startsWith('audio/') ||
    type.startsWith('video/')
  )
}

export function sanitizeDocContent(markdown = '') {
  return normalizeMarkdownText(markdown)
    .replace(IMAGE_MD_RE, '')
    .replace(IMAGE_HTML_RE, '')
}

function quoteMeta(value = '') {
  return JSON.stringify(String(value ?? ''))
}

function parseMetaLine(line = '') {
  const idx = line.indexOf(':')
  if (idx < 0) return null
  const key = line.slice(0, idx).trim()
  const rawValue = line.slice(idx + 1).trim()
  if (!key) return null
  try {
    return [key, JSON.parse(rawValue)]
  } catch {
    return [key, rawValue]
  }
}

function pickFence(content = '') {
  const matches = String(content || '').match(/`{3,}/g) || []
  const maxLen = matches.reduce((max, item) => Math.max(max, item.length), 2)
  return '`'.repeat(maxLen + 1)
}

export function buildDocBlockValue(attrs = {}) {
  const docType = normalizeDocType(attrs.docType)
  const docName = String(attrs.docName || `document.${docType}`)
  const uploadTime = String(attrs.uploadTime || new Date().toISOString())
  const collapsed = Boolean(attrs.collapsed)
  const content = sanitizeDocContent(attrs.content || '')
  return [
    `type: ${quoteMeta(docType)}`,
    `name: ${quoteMeta(docName)}`,
    `uploadTime: ${quoteMeta(uploadTime)}`,
    `collapsed: ${collapsed ? 'true' : 'false'}`,
    '---',
    content,
  ].join('\n')
}

export function parseDocBlockValue(raw = '') {
  const normalized = normalizeMarkdownText(raw)
  const separatorIndex = normalized.indexOf(HEADER_SEPARATOR)
  const headerText = separatorIndex >= 0 ? normalized.slice(0, separatorIndex) : ''
  const bodyText = separatorIndex >= 0 ? normalized.slice(separatorIndex + HEADER_SEPARATOR.length) : normalized
  const attrs = {
    docType: 'txt',
    docName: 'document.txt',
    uploadTime: '',
    collapsed: false,
    content: sanitizeDocContent(bodyText),
  }

  for (const line of headerText.split('\n')) {
    const parsed = parseMetaLine(line)
    if (!parsed) continue
    const [key, value] = parsed
    if (key === 'type') attrs.docType = normalizeDocType(value)
    if (key === 'name' && value) attrs.docName = String(value)
    if (key === 'uploadTime' && value) attrs.uploadTime = String(value)
    if (key === 'collapsed') attrs.collapsed = value === true || value === 'true'
  }

  if (!attrs.docName) attrs.docName = `document.${attrs.docType}`
  return attrs
}

export function buildDocBlockMarkdown(attrs = {}) {
  const value = buildDocBlockValue(attrs)
  const fence = pickFence(value)
  return `${fence}${DOC_BLOCK_FENCE_LANG}\n${value}\n${fence}`
}

export function buildDocContextFence(attrs = {}) {
  const docType = normalizeDocType(attrs.docType)
  const content = sanitizeDocContent(attrs.content || '')
  const fence = pickFence(content)
  return `${fence}${docType}\n${content}\n${fence}`
}

export function buildLegacyDocBlock(attrs = {}) {
  const docType = normalizeDocType(attrs.docType)
  const docName = String(attrs.docName || `document.${docType}`)
  const uploadTime = String(attrs.uploadTime || new Date().toISOString())
  const content = sanitizeDocContent(attrs.content || '')
  return `<doc_type="${docType}" doc_name="${docName}" upload_time="${uploadTime}" collapsed="${Boolean(attrs.collapsed)}">\n${content}\n</doc_end>`
}

export function parseLegacyDocBlock(raw = '') {
  const normalized = normalizeMarkdownText(raw)
  const match = normalized.match(/^<doc_type="([^"]+)"\s+doc_name="([^"]+)"\s+upload_time="([^"]+)"(?:\s+collapsed="([^"]+)")?>\n?([\s\S]*?)\n?<\/doc_end>$/)
  if (!match) return null
  return {
    docType: normalizeDocType(match[1]),
    docName: match[2] || 'document.txt',
    uploadTime: match[3] || '',
    collapsed: match[4] === 'true',
    content: sanitizeDocContent(match[5] || ''),
  }
}

export function extractDocBlockContextFromMarkdown(markdown = '', contentLimit = 0) {
  const normalized = normalizeMarkdownText(markdown)
  const contexts = []
  const appendContext = (attrs) => {
    if (!attrs) return
    const rawContent = String(attrs.content || '')
    if (!rawContent.trim()) return
    contexts.push(buildDocContextFence({
      docType: attrs.docType,
      content: clipDocContext(rawContent, contentLimit),
    }))
  }

  normalized.replace(FENCED_DOC_BLOCK_RE, (_full, _prefix, _fence, value) => {
    appendContext(parseDocBlockValue(value))
    return _full
  })

  normalized.replace(LEGACY_DOC_BLOCK_RE, (full) => {
    appendContext(parseLegacyDocBlock(full))
    return full
  })

  return contexts.join('\n\n')
}

export function transformDocBlockMarkdownForClipboard(markdown = '') {
  const normalized = normalizeMarkdownText(markdown)
  const replacedFence = normalized.replace(FENCED_DOC_BLOCK_RE, (full, prefix, _fence, value) => {
    const attrs = parseDocBlockValue(value)
    return `${prefix}${buildDocContextFence(attrs)}`
  })
  return replacedFence.replace(LEGACY_DOC_BLOCK_RE, (full) => {
    const attrs = parseLegacyDocBlock(full)
    return attrs ? buildDocContextFence(attrs) : full
  })
}

export function stripDocBlockMarkdown(markdown = '') {
  return normalizeMarkdownText(markdown).replace(FENCED_DOC_BLOCK_RE, '$1')
}

export function transformLegacyDocBlocksForExport(markdown = '') {
  return normalizeMarkdownText(markdown).replace(LEGACY_DOC_BLOCK_RE, (full) => {
    const attrs = parseLegacyDocBlock(full)
    return attrs ? buildDocBlockMarkdown(attrs) : full
  })
}

export function transformSpecialDocBlocksToLegacy(markdown = '') {
  return normalizeMarkdownText(markdown).replace(FENCED_DOC_BLOCK_RE, (full, prefix, _fence, value) => {
    const attrs = parseDocBlockValue(value)
    return `${prefix}${buildLegacyDocBlock(attrs)}`
  })
}