#!/bin/bash
# hist_coauthors author.txt


sed 's/ ([12][0-9][0-9][0-9]).*$//;s/&//' $1 |    
   awk -F "[.]," '{for (i=1;i<=NF;i++){print $i}}' |     
   sed 's/^  *//;s/\..*//'  |                           
   sort -t ","             |                           
   tee authors.txt        |                           
   uniq -c               |                           
   sort -nr   >  a
awk '{n+=$1}END{printf "distinct authors: %d\n total authors %d\n",NR,n}' a >b
cat b a > hist_$1
rm a b