#' @title Preprocess an Affymetrix dataset with GC-RMA.
#'
#' @description This function preprocess an Affymetrix dataset using RMA and saves the
#' results in a given TSV file. In addition, it returns the ESET object.
#'
#' The function assumes that a folder containing the raw data exists (as cel files).
#'
#' Note: the function does not check for the existence of folders or files. The batch effect
#' correction is currently not yet supported.
#'
#' @param input_data_dir A string representing the folder that contains the input data.
#' @param output_data_file A string representing the file that should contain the
#'  preprocessed data.
#' @param compressed A boolean representing whether the cel files are compressed. This
#'  is FALSE by default.
#' @param batch_correction A boolean indicating whether batch correction should
#'  be performed, default to FALSE. Note: not yet suported.
#' @param batch_filename A string indicating where the batch information can be found,
#'  default to 'Batch.tsv'. Note: not yet suported.
#' @param clean_samples A boolean indicating whether the dataset should be cleaned by removing
#'  the samples that do not have clinical data. Default to FALSE.
#' @param verbose A boolean representing whether the function should display log information. This
#'  is TRUE by default.
#' @return The expression data as an ESET object.
preprocess_data_affymetrix_gcrma <- function(input_data_dir, output_data_file,
                                           compressed       = FALSE,
                                           batch_correction = FALSE,
                                           batch_filename   = "Batch.tsv",
                                           clean_samples    = FALSE,
                                           verbose          = TRUE) {

  # We define the I/Os.
  raw_data_input_dir <- paste0(input_data_dir, "RAW/")

  # We run the RMA pre-processing method on the data.
  input_data_files <- affy::list.celfiles(raw_data_input_dir, full.names = TRUE)
  remove(raw_data_input_dir)
  batch <- affy::ReadAffy(filenames = input_data_files, compress = compressed, verbose = verbose)
  eset  <- gcrma::gcrma(batch)

  # If necessary, we remove the samples that do not have clinical data.
  if (clean_samples) {
    # We load the clinical data as to get the samples to keep.
    samples <- rownames(Biobase::pData(ArrayUtils::load_clinical_data(input_data_dir,
                                                                      verbose = FALSE)))
    # We only keep the samples with clinical data.
    eset <- eset[, samples]
  }

  # We save the eset data as TSV file.
  utils::write.table(Biobase::exprs(eset), file = output_data_file, sep = "\t", quote = FALSE)

  # We clean up and log information.
  remove(input_data_files, batch)
  if (verbose == TRUE) {
    message(paste0("[", Sys.time(), "] Expression data pre-processed with RMA."))
  }

  # We return the created ESET.
  return(eset)
}