| awk ' # deroman |
| # Input: string (tab) [arab or roman] |
| # Output: string (tab) [arab] |
| |
| # Roman numeral n is replaced by arab n-1000 (e.g., iii -> -997) |
| BEGIN { FS = OFS = "\t" |
| # set a["i"] = 1, a["ii"] = 2, ... |
| s = "i ii iii iv v vi vii viii ix x" |
| s = s " xi xii xiii xiv xv xvi xvii xviii xix xx" |
| s = s " xxi xxii xxiii xxiv xxv xxvi xxvii xxviii xxix xxx" |
| n = split(s, b, " ") |
| for (i = 1; i <= n; i++) a[b[i]] = i |
| } |
| $2~/^[ivxlc]+$/ { if ($2 in a) $2 = -1000 + a[$2] |
| else print "deroman: bad number: " $0 | "cat 1>&2" |
| } |
| { print } |
| ' $* |
