#!/bin/bash

# Create a tally of all the words in the corpus.
#
echo Creating tally of word frequencies...
sed -e 's/ /\n/g' -e 's/[^a-zA-Z\n]//g' corpus.txt | \
  tr [:upper:] [:lower:] | \
  sort | \
  uniq -c | \
  sort -rn > frequency.txt

echo Creating corpus lexicon...
rm -f corpus-lexicon.txt

for i in $(awk '{if( $2 ) print $2}' frequency.txt); do
  grep -m 1 ^$i\$ dictionary.txt >> corpus-lexicon.txt;
done

echo Creating lexicon...
rm -f lexicon.txt

for i in $(cat corpus-lexicon.txt); do
  egrep -m 1 "^[0-9 ]* $i\$" frequency.txt | \
    awk '{print $2, $1}' | \
    tr ' ' ',' >> lexicon.txt;
done