1.1 --- /dev/null	Thu Jan 01 00:00:00 1970 +0000
     1.2 +++ b/stuff/wordfreq	Mon Oct 20 07:09:57 2014 +0200
     1.3 @@ -0,0 +1,10 @@
     1.4 +#!/bin/sh
     1.5 +#
     1.6 +# print word frequency
     1.7 +
     1.8 +deroff "$@" |
     1.9 +        tr -c 'A-Za-zÄÖÜäöüß-' '\n' | tr A-ZÄÖÜ a-zäöü |
    1.10 +	sed '/^ *$/d'| sort |uniq -c | awk '
    1.11 +{sum+=$1; a[$2]=$1;}
    1.12 +END {for (x in a) {printf("%s\t%.2f\t%4d\n", x, a[x]/sum, a[x])} }
    1.13 +'| sort -nr -k 3