#!/usr/bin/awk -f # only for mostly 2-byte encodings like euc-kr $2~"^/x..$" { c = substr($2, 3, 2) if (c<"80") print substr($1, 3, 4) "\t" c } $2~"^/x../x..$" { print substr($1, 3, 4) "\t" substr($2, 3, 2) substr($2, 7, 2) }