#!/bin/sh
# Produce a sorted list of words present in the input file
sed -e '/^-----File: .*\.png---------------------------------------------------------$/d' -e '/^\[Blank Page\]$/d' -e 's/\[\*\*[^]]*\]//g' -e 's/<[^>]*>//g' \
  -e 's/\[Illustration//g' -e '/^\/[#\*]$/d' -e '/^[#\*]\/$/d' $1 | \
awk '{ \
    gsub("[^[:alnum:]\047*-]+"," ",$0); \
    print; \
}' | tr ' ' '\n' | \
  perl -e 'while(<>) { $_ =~ s/([[:alpha:]])/\L\1\E/g; print; }' | \
  sed -e '/^$/d' -e "/^'$/d" -e '/^[0-9]*$/d' | sort
