R/fara.R

In abresler/govtrackR: Federal government tracking tools

.ocr_fara_url <-
  function(url = "https://efile.fara.gov/docs/2244-Informational-Materials-20200410-14.pdf", return_message  = T) {
    if (return_message) {
      glue("OCR'ing {url}") %>% message()
    }
    data <- pdftools::pdf_info(url) %>% flatten_df()
    text <- url %>% pdftools::pdf_text()
    text <- text %>% str_split(pattern = "\n") %>%
      flatten_chr() %>%
      str_squish() %>%
      discard(list(function(x) {
        x == ""
      })) %>%
      discard(list(function(x){
        x %>% str_detect("Received by NSD/FARA|[0-9]")
      })) %>%
      str_c(collapse = " | ")
    data %>%
      mutate(text_pdf = text,
             url_document_fara = url)
  }

#' OCR FARA PDFs
#'
#' reads
#'
#' @param urls
#' @param return_message
#'
#' @return
#' @export
#'
#' @examples
#' ocr_fara_urls(urls = "https://efile.fara.gov/docs/2244-Informational-Materials-20200410-14.pdf")
ocr_fara_urls <-
  function(urls,
           seperate_text = F,
           return_message = T) {
    .ocr_fara_url_safe <- possibly(.ocr_fara_url, tibble())

    data <-
      urls %>%
      future_map_dfr(function(x) {
        .ocr_fara_url_safe(url = x, return_message = return_message)
      })

    data <-
      data %>%
      mutate_if(is.character, list(function(x) {
        case_when(x == "" ~ NA_character_,
                  TRUE ~ x)
      })) %>%
      .remove_na()

    if (seperate_text) {
      data <-
        data %>%
        separate_rows(text_pdf, sep = "\\|") %>%
        mutate_if(is.character, str_trim)
    }

    data
  }

# dictionaries ------------------------------------------------------------


.dictionary_fara_names <-
  function() {
    tibble(
      nameFARA = c(
        "Short Form Termination Date",
        "Short Form Date",
        "Short Form Last Name",
        "Short Form First Name",
        "Registration Number",
        "Registration Date",
        "Registrant Name",
        "Address 1",
        "Address 2",
        "City",
        "State",
        "Zip",
        "Termination Date",
        "Name",
        "Business Name",
        "Foreign Principal Termination Date",
        "Foreign Principal",
        "Foreign Principal Registration Date",
        "Country/Location Represented",
        "Registrant Date",
        "Foreign_principal",
        "FP_registration_date",
        "Country_location_represented",
        "Registration_number",
        "Registration_date",
        "Registrant_name",
        "Address_1",
        "Address_2",
        "FP_termination_date",
        "Registration_Number",
        "Registration_Date",
        "Termination_Date",
        "Business_Name",
        "CDATE_STAMPED",
        "REGISTRANT_NAME",
        "REGISTRATION_NUMBER",
        "DOCUMENT_TYPE",
        "URL",
        "SHORT_FORM_NAME",
        "FOREIGN_PRINCIPAL_NAME",
        "FOREIGN_PRINCIPAL_COUNTRY",
        "Short_form_last_name",
        "Short_form_first_name",
        "Short_form_date",
        "Short_form_termination_date"
      ),
      nameActual =
        c(
          "dateShortFormTermination",
          "dateShortForm",
          "nameLastShortForm",
          "nameFirstShortForm",
          "idFARA",
          "dateRegistration",
          "nameRegistrant",
          "addressStreet1Registrant",
          "addressStreet2Registrant",
          "cityRegistrant",
          "stateRegistrant",
          "zipcodeRegistrant",
          "dateTermination",
          "nameRegistrant",
          "nameRegistrantEntity",
          "dateTerminationForeignPrincipal",
          "nameForeignPrincipal",
          "dateRegistrationForeignPrincipal",
          "countryForeignPrincipal",
          "dateRegistrant",

          "nameForeignPrincipal",
          "dateRegistrationForeignPrincipal",
          "countryForeignPrincipal",
          "idFARA",
          "dateRegistration",
          "nameRegistrant",
          "addressStreet1Registrant",
          "addressStreet2Registrant",
          "dateTerminationForeignPrincipal",

          "idFARA",
          "dateRegistration",
          "dateTermination",
          "nameRegistrantEntity",

          "dateDocumentFARA",
          "nameRegistrant",
          "idFARA",
          "typeDocument",
          "urlDocumentFARA",
          "nameShortForm",
          "nameForeignPrincipal",
          "countryForeignPrincipal",
          "nameLastShortForm",
          "nameFirstShortForm",
          "dateShortForm",
          "dateShortFormTermination"
        )
    )
  }


.munge_fara_names <-
  function(data) {
    dict_names <- .dictionary_fara_names()
    fdps_names <-
      names(data)

    actual_names <-
      fdps_names %>%
      map_chr(function(name) {
        df_row <-
          dict_names %>% filter(nameFARA == name)
        if (nrow(df_row) == 0) {
          glue::glue("Missing {name}") %>% message()
          return(name)
        }

        df_row$nameActual
      })

    data %>%
      set_names(actual_names)
  }



# parse -------------------------------------------------------------------

.parse_fara_xml <-
  function(url = "https://efile.fara.gov/bulk/zip/FARA_All_ForeignPrincipals.xml.zip", return_message = T) {
  tmp <-
    tempfile()

  file <- curl_download(url, tmp)

  unz_files <- unzip(file, exdir = "xml")
  typeFile <- url %>% str_split("/") %>% flatten_chr() %>%
    keep(function(x) {
      x %>% str_detect(".xml")
    }) %>%
    str_remove_all(".xml.zip")

  data <- read_xml(unz_files)
  unz_files %>% unlink()
  file %>% unlink()
  unlink("xml", recursive = T)
  doc <- data %>% xml_contents()
  rm(data)
  gc()

  data <- 1:length(doc) %>%
    map_dfr(function(x) {
      glue("Parsing node {x}") %>% message()
      doc[[x]] %>% as_list() %>% flatten_df()
    })

  rm(doc)

  data <-
    data %>%
    .munge_fara_names() %>%
    .munge_data(clean_address = F) %>%
    mutate(urlFARA = url,
           typeFile) %>%
    select(typeFile, everything())

  if (return_message) {
    items <- nrow(data) %>% comma(digits = 0)
    file_name <-
      typeFile %>% str_replace_all("\\_", " ") %>% str_trim()
    glue("Found {items} items under {file_name}") %>% message()
  }
  gc()
  data

}

.parse_fara_csv <-
  function(url = "https://efile.fara.gov/bulk/zip/FARA_All_Registrants.csv.zip",
           return_message = T) {
    tmp <-
      tempfile()

    file <- curl_download(url, tmp)

    unz_files <- unzip(file, exdir = "xml")

    data <- unz_files %>% fread(verbose = F,showProgress = FALSE) %>% as_tibble()
    unz_files %>% unlink(recursive = T)
    file %>% unlink(force = T)
    tmp %>% unlink(force = T)
    unlink("xml", recursive = T)
    typeFile <- url %>% str_split("/") %>% flatten_chr() %>%
      keep(function(x) {
        x %>% str_detect(".csv")
      }) %>%
      str_remove_all(".csv.zip")

    data <-
      data %>%
      .munge_fara_names()

    data <-
      data %>%
      .munge_data(clean_address = F) %>%
      mutate(urlFARA = url,
             typeFile) %>%
      select(typeFile, everything())

    if (return_message) {
      items <- nrow(data) %>% comma(digits = 0)
      file_name <-
        typeFile %>% str_replace_all("\\_", " ") %>% str_trim()
      glue("Found {items} items under {file_name}") %>% message()
    }


    gc()
    data
  }

.parse_fara_csv_m <- memoise::memoise(.parse_fara_csv)

.parse_fara_xml_m <- memoise::memoise(.parse_fara_xml)

# functions ---------------------------------------------------------------


#' FARA registered entities
#'
#' Acquires all FARA registered representitives.
#' This includes information about the agents including
#' their location, periods of active work
#'
#'
#' @param method method of bulk download \itemize{
#' \item xml - default and returns all historic matches
#' \item csv - returns only a portion of registrants
#' }
#' @param only_active if \code{TRUE} returns only active registrants
#' @param return_message if \code{TRUE} returns message
#'
#' @return
#' @export
#'
#' @examples
#' \dontrun{
#' fara_registrants(method = "xml")
#' }
fara_registrants <-
  function(method = "xml",
           only_active = F,
           return_message = T) {

    if (str_to_lower(method) == "xml") {
      data <- .parse_fara_xml_m(url = "https://efile.fara.gov/bulk/zip/FARA_All_Registrants.xml.zip", return_message = return_message)
    } else {
      data <- .parse_fara_csv_m(url = "https://efile.fara.gov/bulk/zip/FARA_All_Registrants.csv.zip", return_message = T)
    }



    data <- data %>%
      mutate_if(is.character,
                str_trim) %>%
      mutate_if(is.character,
                list(function(x) {
                  if_else(x == "", NA_character_, x)
                })) %>%
      mutate_at(data %>% select(matches("address")) %>% names(),
                list(function(x) {
                  x %>% str_remove_all("-") %>% str_trim()
                })) %>%
      mutate(
        dateRegistrationClean = dateRegistration,
        dateTerminationClean = dateTermination,
        dateRegistration = case_when(
          is.na(dateRegistration) ~ dateRegistration,
          dateRegistrationClean > dateTerminationClean ~ dateTerminationClean,
          TRUE ~ dateRegistrationClean
        ),
        dateTermination = case_when(
          is.na(dateTermination) ~ dateTermination,
          dateTerminationClean < dateRegistrationClean ~ dateRegistrationClean,
          TRUE ~ dateTerminationClean
        ),
      ) %>%
      select(-c(dateRegistrationClean, dateTerminationClean)) %>%
      mutate(
        isActiveEntityFARA = is.na(dateTermination),
        countDaysActiveEntityFARA = case_when(
          isActiveEntityFARA ~ (Sys.Date() - dateRegistration) %>% as.integer(),
          TRUE ~ (dateTermination - dateRegistration) %>% as.integer()
        ),
        addressStreet = case_when(
          is.na(addressStreet2Registrant) &
            !is.na(addressStreet1Registrant) ~ addressStreet1Registrant,
          !is.na(addressStreet1Registrant) &
            !is.na(addressStreet1Registrant) ~ str_c(addressStreet1Registrant, addressStreet2Registrant, sep = " "),
          TRUE ~ NA_character_
        ),
        cityState = case_when(
          is.na(stateRegistrant) &
            !is.na(cityRegistrant) ~ cityRegistrant,
          !is.na(stateRegistrant) &
            !is.na(cityRegistrant) ~ str_c(cityRegistrant, stateRegistrant, sep = ", "),
          TRUE ~ NA_character_
        ),
        addressCity = case_when(
          is.na(cityState) &
            !is.na(addressStreet) ~ addressStreet,
          !is.na(cityState) &
            !is.na(addressStreet) ~ str_c(addressStreet, cityState, sep = " "),
          TRUE ~ NA_character_
        ),
        locationRegistrant = case_when(
          is.na(zipcodeRegistrant) & !is.na(addressCity) ~ addressCity,
          !is.na(zipcodeRegistrant) &
            !is.na(addressCity) ~ str_c(addressCity, zipcodeRegistrant, sep = " "),
          TRUE ~ NA_character_
        )
      ) %>%
      select(-c(addressCity, cityState, addressStreet)) %>%
      select(
        idFARA,
        isActiveEntityFARA,
        idFARA,
        countDaysActiveEntityFARA,
        dateRegistration,
        dateTermination,
        nameRegistrant,
        nameRegistrantDetail,
        nameRegistrantEntity,
        locationRegistrant,
        everything()
      )

    if (only_active) {
      data <- data %>%
        filter(isActiveEntityFARA)
    }

    #### fix entities

    data
  }


#' FARA Foreign Principals
#'
#' Acquires all FARA foreign principals.  This includes
#' information about the foreign princpial, their FARA agent and
#' period of registration.
#'
#' @param method method of bulk download \itemize{
#' \item xml - default and returns all historic matches
#' \item csv - returns only a portion of foreign principals
#' }
#' @param only_active if \code{TRUE} returns only active foreign principals
#' @param return_message if \code{TRUE} returns a message
#' @return \code{tibble}
#' @export
#'
#' @examples
#' \dontrun{
#' fara_principals(method = "xml")
#' }
fara_principals <-
  function(method = "xml",
           only_active = F,
           return_message = T) {

    if (str_to_lower(method) == "xml") {
      data <-
        .parse_fara_xml_m(url = "https://efile.fara.gov/bulk/zip/FARA_All_ForeignPrincipals.xml.zip", return_message = return_message)
    } else {
      data <-
        .parse_fara_csv_m(url = "https://efile.fara.gov/bulk/zip/FARA_All_ForeignPrincipals.csv.zip", return_message = return_message)
    }


    data <-
      data %>%
      mutate(
        dateRegistrationClean = dateRegistrationForeignPrincipal,
        dateTerminationClean = dateTerminationForeignPrincipal,
        dateRegistrationForeignPrincipal = case_when(
          is.na(dateRegistrationForeignPrincipal) ~ dateRegistrationForeignPrincipal,
          dateRegistrationClean > dateTerminationClean ~ dateTerminationClean,
          TRUE ~ dateRegistrationClean
        ),
        dateTerminationForeignPrincipal = case_when(
          is.na(dateTerminationForeignPrincipal) ~ dateTerminationForeignPrincipal,
          dateTerminationClean < dateRegistrationClean ~ dateRegistrationClean,
          TRUE ~ dateTerminationClean
        ),
      ) %>%
      select(-c(dateRegistrationClean, dateTerminationClean)) %>%
      mutate(
        isActiveForeignPrincipal = is.na(dateTerminationForeignPrincipal),
        countDaysActiveForeignPrincipalFARA = case_when(
          isActiveForeignPrincipal ~ (Sys.Date() - dateTerminationForeignPrincipal) %>% as.integer(),
          TRUE ~ (
            dateTerminationForeignPrincipal - dateRegistrationForeignPrincipal
          ) %>% as.integer()
        )
      )

    data <-
      data %>%
      mutate_if(is.character,
                str_trim) %>%
      mutate_if(is.character,
                list(function(x) {
                  if_else(x == "", NA_character_, x)
                })) %>%
      mutate_at(data %>% select(matches("address")) %>% names(),
                list(function(x) {
                  x %>% str_remove_all("-") %>% str_trim()
                })) %>%
      mutate(
        addressStreet = case_when(
          is.na(addressStreet2Registrant) &
            !is.na(addressStreet1Registrant) ~ addressStreet1Registrant,
          !is.na(addressStreet1Registrant) &
            !is.na(addressStreet1Registrant) ~ str_c(addressStreet1Registrant, addressStreet2Registrant, sep = " "),
          TRUE ~ NA_character_
        ),
        cityState = case_when(
          is.na(stateRegistrant) &
            !is.na(cityRegistrant) ~ cityRegistrant,
          !is.na(stateRegistrant) &
            !is.na(cityRegistrant) ~ str_c(cityRegistrant, stateRegistrant, sep = ", "),
          TRUE ~ NA_character_
        ),
        addressCity = case_when(
          is.na(cityState) &
            !is.na(addressStreet) ~ addressStreet,
          !is.na(cityState) &
            !is.na(addressStreet) ~ str_c(addressStreet, cityState, sep = " "),
          TRUE ~ NA_character_
        ),
        locationRegistrant = case_when(
          is.na(zipcodeRegistrant) & !is.na(addressCity) ~ addressCity,
          !is.na(zipcodeRegistrant) &
            !is.na(addressCity) ~ str_c(addressCity, zipcodeRegistrant, sep = " "),
          TRUE ~ NA_character_
        )
      ) %>%
      select(-c(addressCity, cityState, addressStreet))

    clean_names <-
      data %>% select(-one_of(c("dateRegistrant", "nameRegistrant", "nameRegistrantDetail", "typeRegistrant"))) %>% select(matches("Registrant")) %>% names()

    names(data)[names(data) %in% clean_names] <-
      names(data)[names(data) %in% clean_names] %>% str_replace_all("Registrant", "ForeignPrincipal")

    data <-
      data %>%
      select(
        typeFile,
        isActiveForeignPrincipal,
        dateRegistrationForeignPrincipal,
        countryForeignPrincipal,
        nameForeignPrincipal,
        nameRegistrant,
        countDaysActiveForeignPrincipalFARA,
        dateRegistrationForeignPrincipal,
        locationForeignPrincipal,
        everything()
      )


    if (only_active) {
      data <-
        data %>%
        filter(isActiveForeignPrincipal)
    }

    data
  }

#' FARA filed documents
#'
#' Acquires data for all available FARA documents.
#' This includes information about ther foreign principal,
#' registrant and FARA document type.
#'
#' @param method method of bulk download \itemize{
#' \item xml - default and returns all historic matches
#' \item csv - returns only a portion of registrants' documents
#' }
#' @param only_active if \code{TRUE} returns only documents available online
#' @param return_message if \code{TRUE} returns a message
#'
#' @return
#' @export
#'
#' @examples
#' \dontrun{
#' fara_documents(method = "xml")
#' }
fara_documents <-
  function(method = "xml",
           only_active = F,
           snake_names = T,
           return_message = T) {
    if (str_to_lower(method) == "xml") {
      data <-
        .parse_fara_xml_m(url = "https://efile.fara.gov/bulk/zip/FARA_All_RegistrantDocs.xml.zip", return_message = return_message)
    } else {
      data <-
        .parse_fara_csv_m(url = "https://efile.fara.gov/bulk/zip/FARA_All_RegistrantDocs.csv.zip", return_message = return_message)
    }

    data <-
      data %>%
      mutate(isDocumentAvailableOnline = urlDocumentFARA != "available-fara-public-office") %>%
      select(typeFile, isDocumentAvailableOnline, everything())

    data <- data %>%
      filter(isDocumentAvailableOnline) %>%
      mutate(
        urlDocumentFARA = case_when(
          typeDocument == "AMENDMENT" ~ urlDocumentFARA %>% str_replace_all("amendment", "Amendment;"),
          typeDocument == "SHORT-FORM" ~ urlDocumentFARA %>% str_replace_all("short-form", "Short-Form;"),
          typeDocument == "EXHIBIT AB" ~ urlDocumentFARA %>% str_replace_all("exhibit-ab", "Exhibit-AB;"),
          typeDocument == "SUPPLEMENTAL STATEMENT" ~ urlDocumentFARA %>% str_replace_all("supplemental-statement", "Supplemental-Statement;"),
          typeDocument == "EXHIBIT C" ~ urlDocumentFARA %>% str_replace_all("exhibit-c", "Exhibit-C;"),
          typeDocument == "REGISTRATION STATEMENT" ~ urlDocumentFARA %>% str_replace_all("registration-statement", "Registration-Statement;"),
          typeDocument == "INFORMATIONAL MATERIALS" ~ urlDocumentFARA %>% str_replace_all("informational-materials", "Informational-Materials;"),
          typeDocument == "EXHIBIT D" ~ urlDocumentFARA %>% str_replace_all("exhibit-d", "Exhibit-D;"),
          typeDocument == "CONFLICT PROVISION" ~ urlDocumentFARA %>% str_replace_all("conflict-provision", "Conflict-Provision;"),
          typeDocument == "DISSEMINATION REPORT" ~ urlDocumentFARA %>% str_replace_all("dissemination-report", "Dissemination-Report;")
        )
      ) %>%
      separate(urlDocumentFARA,
               into = c("url1", "url2"),
               extra = "merge",
               sep = "\\;") %>%
      mutate(
        url2 = url2 %>% str_remove_all("\\.pdf") %>% str_to_upper() %>% str_c(".pdf") %>% str_remove_all("\\.pdf") %>% str_to_upper() %>% str_c(".pdf")
      ) %>%
      unite(urlDocumentFARA,
            url1,
            url2,
            sep = "") %>%
      bind_rows(data %>% filter(!isDocumentAvailableOnline)) %>%
      arrange(dateDocumentFARA) %>%
      mutate(
        urlDocumentFARA = case_when(
          urlDocumentFARA == "available-fara-public-office" ~ NA_character_,
          TRUE ~ urlDocumentFARA
        )
      )

    data <- data %>%
      mutate(
        nameShortForm = nameShortForm %>% str_remove_all(", RT|\\, DIRECTOR|\\:") %>%
          str_replace_all("\\, JR", "\\ JR") %>%
          str_replace_all("\\, SR", "\\ SR") %>%
          str_replace_all(", III", "\\ III")
      )

    df_names <- data %>%
      filter(!is.na(nameShortForm)) %>%
      distinct(nameShortForm) %>%
      mutate(nameShortFormClean = rm_bracket(nameShortForm))

    df_names <-
      df_names %>%
      filter(nameShortForm %>% str_detect("\\,")) %>%
      separate(nameShortFormClean, into = c("nameLast", "nameFirst"), sep = "\\,",
               extra = "merge",
               convert = T) %>%
      mutate_all(str_trim) %>%
      unite(nameShortFormClean, nameFirst, nameLast, sep = " ") %>%
      bind_rows(
        df_names %>% filter(!nameShortFormClean %>% str_detect("\\,"))
      )

    data <-
      data %>%
      left_join(df_names, by = "nameShortForm") %>%
      select(-nameShortForm) %>%
      rename(nameShortForm = nameShortFormClean) %>%
      select(one_of(names(data)), everything()) %>%
      select(
        typeFile:dateDocumentFARA,
        typeDocument,
        idFARA,
        nameRegistrant,
        nameRegistrantDetail,
        nameShortForm,
        countryForeignPrincipal,
        nameForeignPrincipal,
        nameForeignPrincipalDetail,
        typeForeignPrincipal,
        everything()
      ) %>%
      arrange(desc(dateDocumentFARA))

    if (only_active) {
      data <-
        data %>%
        filter(isDocumentAvailableOnline)
    }

    if (snake_names) {
      data <- data %>%
        clean_names()
    }

    data

  }

#' FARA short-form data
#'
#' Acquires all FARA short form filer data.
#' This includes information about FARA registrants and
#' their employees.
#'
#' @param method method of bulk download \itemize{
#' \item xml
#' \item csv
#' }
#' @param only_active if
#' @param return_message if \code{TRUE} returns a message
#'
#' @return \code{tibble}
#'
#' @export
#'
#' @examples
#' \dontrun{
#' fara_short_forms()
#' }
fara_short_forms <-
  function(method = "xml",
           only_active = F,
           return_message = T) {
    if (str_to_lower(method) == "xml") {
      data <-
        .parse_fara_xml_m(url = "https://efile.fara.gov/bulk/zip/FARA_All_ShortForms.xml.zip", return_message = return_message)
    } else {
      data <-
        .parse_fara_csv_m(url = "https://efile.fara.gov/bulk/zip/FARA_All_ShortForms.csv.zip", return_message = return_message)
    }

    data <-
      data %>%
      mutate_if(is.character,
                str_trim) %>%
      mutate_if(is.character,
                list(function(x) {
                  if_else(x == "", NA_character_, x)
                })) %>%
      mutate_at(data %>% select(matches("address")) %>% names(),
                list(function(x) {
                  x %>% str_remove_all("-") %>% str_trim()
                })) %>%
      mutate(
        isActiveEntityFARA = is.na(dateShortFormTermination),
        countDaysActiveEntityFARA = case_when(
          isActiveEntityFARA ~ (Sys.Date() - dateRegistration) %>% as.integer(),
          TRUE ~ (dateShortFormTermination - dateRegistration) %>% as.integer()
        ),
        addressStreet = case_when(
          is.na(addressStreet2Registrant) &
            !is.na(addressStreet1Registrant) ~ addressStreet1Registrant,
          !is.na(addressStreet1Registrant) &
            !is.na(addressStreet1Registrant) ~ str_c(addressStreet1Registrant, addressStreet2Registrant, sep = " "),
          TRUE ~ NA_character_
        ),
        cityState = case_when(
          is.na(stateRegistrant) &
            !is.na(cityRegistrant) ~ cityRegistrant,
          !is.na(stateRegistrant) &
            !is.na(cityRegistrant) ~ str_c(cityRegistrant, stateRegistrant, sep = ", "),
          TRUE ~ NA_character_
        ),
        addressCity = case_when(
          is.na(cityState) &
            !is.na(addressStreet) ~ addressStreet,
          !is.na(cityState) &
            !is.na(addressStreet) ~ str_c(addressStreet, cityState, sep = " "),
          TRUE ~ NA_character_
        ),
        locationRegistrant = case_when(
          is.na(zipcodeRegistrant) & !is.na(addressCity) ~ addressCity,
          !is.na(zipcodeRegistrant) &
            !is.na(addressCity) ~ str_c(addressCity, zipcodeRegistrant, sep = " "),
          TRUE ~ NA_character_
        )
      ) %>%
      select(-c(addressCity, cityState, addressStreet)) %>%
      unite(
        nameShortForm,
        nameFirstShortForm,
        nameLastShortForm,
        sep = " ",
        remove = F
      ) %>%
      select(
        idFARA,
        isActiveEntityFARA,
        countDaysActiveEntityFARA,
        idFARA,
        nameShortForm,
        nameRegistrant,
        matches("date"),
        locationRegistrant,
        everything()
      )

    data
  }