library('biomaRt')
library('tidyr')
library('stringr')
library('dplyr')
library('sqldf')
library('stringi')
library('optparse')

option_list = list(
  make_option(c("-f", "--file"), type="character", default=NULL,
              help="file name", metavar="character"),
  make_option(c("-n", "--file2"), type="character", default=NULL,
              help="file name2", metavar="character"),
  make_option(c("-c", "--code"), type="character", default=NULL,
              help="code", metavar="character"),
  make_option(c("-o", "--out"), type="character", default="results2.csv",
              help="output file name with full path [default= %default]", metavar="character")
);

opt_parser = OptionParser(option_list=option_list);
opt = parse_args(opt_parser);


if (is.null(opt$file)){
  print_help(opt_parser)
  stop(" At least 2 arguments must be supplied (2 input files).n", call.=FALSE)
}

f=opt$file
f2=opt$file2
filetowrite=opt$out
code=opt$code

print("Reading file")

df_raw = read.csv(f, sep ='\t', header = FALSE,na.strings=c("", " ","NA"))
colnames(df_raw) <- c("id","chr","pos")
df_raw$id <- gsub(" ", "", df_raw$id, fixed = TRUE)

print("Reading file 2")

df = read.csv(f2, sep ='\t', header = FALSE,na.strings=c("", " ","NA"))
colnames(df) <- c("id_R2", "tail_seq")
df2 <- df %>% separate(id_R2,c("id_R","garbage"), sep=" ")
df2$garbage <- NULL

merged = sqldf("
    SELECT *
    FROM df_raw d1 JOIN df2 d2
    ON d1.id = d2.id_R
  ")

merged$code <- code
df3 <- select(merged,"id","tail_seq","chr","pos","code")
write.table(df3, filetowrite, sep="\t", quote=FALSE, row.names=FALSE, col.names=FALSE)