- BEGIN { FS = "[] \t\n\r!\"#'\''()*+,./:;<=>?\\^_`{|}~[-]+" }
- { for (n = 1; n <= NF; n++) if ( $n != "" ) { words[tolower($n)]++; total++; } }
+ BEGIN { FS = "([] \t\n\r!\"#'\''()*+,./:;<=>?\\^_`{|}~[-]|%[0-9A-Fa-f]{2})+" }
+ { for (n = 1; n <= NF; n++) {
+ if ( $n != "" && length($n) <= 128 ) {
+ words[tolower($n)]++; total++;
+ } } }