mtt/R/create_glossardict.R

create_glossardict <- function(artworks, glossar_files, xmlpath) {

  x <- NULL
  
  for (glossar_file in glossar_files) {
    for (artwork in artworks) {
      fnames <- dir(pattern = paste0(artwork, "_"), path = paste0(xmlpath, artwork))
      for (fname in fnames) {
        suppressWarnings(
          lines <- readLines(paste0(xmlpath, artwork, "/", fname))
        )
        if (any(grepl(glossar_file, lines))) {
          x <- rbind(x, data.frame(glossar_file, artwork))
          break   # if one match is found, we are done
        }
      }
    }
  }
  tapply(x$artwork, x$glossar_file, FUN = c)
}
# TODO: Get rid of (at least 2) loops
# TODO: Add progress bars