data.table fread fixed width file reader

flat_fread.R

# for reading fixed with files, which are files with no delimiter (see readr package and read_fwf())
# col_widths is a vector of column widths (e.g., c(8, 4, 2, 9))
# input file is a character string with the input file (e.g., "./data/read.txt")
# on 300 MB file with 143 columns timings on 2018 Macbook pro were as follows:
# read_fwf from readr package:  10.8 sec
# non-parallel use of gawk:  10.5 sec
# parallel use of gawk:  4.4 sec (below function)

flat_fread <- function(col_widths, input_file){
    col_spec <- paste0(widths, collapse = " ")
    gawk_string <- paste0("parallel --pipepart -a ", input_file, " gawk \\'\\$1=\\$1\\' FIELDWIDTHS=\\'", col_spec, "\\' OFS=,")
    dt <- fread(cmd = gawk_string, header = FALSE, stringsAsFactors = FALSE)
    return(dt)
}