#! /bin/sh
#
# wordcount
# count words in a CES file after </cesheader> ommiting all tags
# script from Heiki-Jaan Kaalep (hkaalep@psych.ut.ee)
# requires gnu sed and possibly gnu grep
# 
sed '1,/<\/cesheader>/d' | \
sed 's/</{</g' | sed 's/>/>{/g' | \
tr '{' '\012' | grep -v '>' | grep -v '<' | \
sed 's/^[\.,;:?\!()] //g' | \
sed 's/^[\.,;:?\!()]$//g' | wc -w