pdf-extract-Via_Software/src/utils/regex/regexMapaFolha.ts

const regexMapaFolha = {
  companyName: (): RegExp => /Empresa\s*:\s*(?<companyName>.*?)\s*\(\s*(\d{1,})\s*\)\s*Página/gm,

  companyCode: (): RegExp => /Empresa\s*:\s*.*?\s*\(\s*(?<companyCode>\d{1,})\s*\)\s*Página/gm,

  companyAddress: (): RegExp => /End\.\s*:\s*(?<companyAddress>.*?)CNPJ\/CEI/gm,

  /**
   * Em caso de endereços grande pode quebrar o CNPJ por isso estou pegando qualquer ocorrencia de 14 caracteres numericos entre "CNPJ/CEI" e "Ref"
   * até o momento não teve caso de partir o cnpj no meio
   */
  companyCNPJ: (): RegExp => /CNPJ\/CEI:((.|\n)*?)(?<companyCNPJ>\d{14})((.|\n)*?)Ref\.:/gm,

  reportReference: (): RegExp =>
    /Ref\.:\s*(?<refStartDate>\d{2}\/\d{2}\/\d{4})\s*a\s*(?<refEndDate>\d{2}\/\d{2}\/\d{4})/gm,

  contentEmployePage: (): RegExp =>
    /Ref\.:\s*\d{2}\/\d{2}\/\d{4}\s*a\s*\d{2}\/\d{2}\/\d{4}(.*?)\n{1,}(?<contentEmployePage>(.|\n)*)/gm,

  employeeInfo: (): RegExp =>
    /^(?<employeeCode>\d{1,})\s*(?<employeeName>.*?)(?<employeeSalary>(\.?\d{1,}){1,},\d{2})\s*Função\s*:(?<employeeRole>(.|\n)*?)(?<employeeContentRest>Livro(.|\n)*?Base INSS:.*$)/gm,

  employeeAdmissionDate: (): RegExp =>
    /Admissão\s*:\s*(?<employeeAdmissionDate>\d{2}\/\d{2}\/\d{4})/gm,

  employeeEvents: (): RegExp => /Admissão\s*:(.*?)\n(?<events>(.|\n)*?)(.*)\n\s*\*{5,}/gm,

  eventReference: (): RegExp => /.*?\s{2,}(?<eventReference>.*?)\s{2,}.*/g,

  eventInfo: (): RegExp => /^(?<eventCode>\d{1,})\s*(?<eventDescription>(.*?))\s{2}/g,

  inss: (): RegExp => /Base\sINSS:(?<baseINSS>.*?)\(Aliq\.:(?<aliquotINSS>(.*?))%\)/gm,

  fgts: (): RegExp => /Base\sFGTS:(?<baseFGTS>.*?)\(Valor:(?<valueFGTS>(.*?))\)/gm,

  baseIRRF: (): RegExp => /Base\sIRRF\sFolha:\s(?<baseIRRF>.{1,15})/gm,
};

export default regexMapaFolha;