Class DocParser

apps/sim/lib/file-parsers/doc-parser.ts:9–130

const logger = createLogger('DocParser')

export class DocParser implements FileParser {
  async parseFile(filePath: string): Promise<FileParseResult> {
    try {
      if (!filePath) {
        throw new Error('No file path provided')
      }

      if (!existsSync(filePath)) {
        throw new Error(`File not found: ${filePath}`)
      }

      const buffer = await readFile(filePath)
      return this.parseBuffer(buffer)
    } catch (error) {
      logger.error('DOC file parsing error:', error)
      throw new Error(`Failed to parse DOC file: ${(error as Error).message}`)
    }
  }

  async parseBuffer(buffer: Buffer): Promise<FileParseResult> {
    try {
      if (!buffer || buffer.length === 0) {
        throw new Error('Empty buffer provided')
      }

      try {
        const officeParser = await import('officeparser')
        const result = await officeParser.parseOfficeAsync(buffer)

        if (result) {
          const resultString = typeof result === 'string' ? result : String(result)
          const content = sanitizeTextForUTF8(resultString.trim())

          if (content.length > 0) {
            return {
              content,
              metadata: {
                characterCount: content.length,
                extractionMethod: 'officeparser',
              },
            }
          }
        }
      } catch (officeError) {
        logger.warn('officeparser failed, trying mammoth:', officeError)
      }

      try {
        const mammoth = await import('mammoth')
        const result = await mammoth.extractRawText({ buffer })

        if (result.value && result.value.trim().length > 0) {
          const content = sanitizeTextForUTF8(result.value.trim())
          return {
            content,
            metadata: {
              characterCount: content.length,
              extractionMethod: 'mammoth',