#! /usr/bin/env bash

# see http://fabien.benetou.fr/innovativ.it/www/HistoricalArchives/Seedea/Oimp/Ubiquitousvocabulary

LOGS=web/thelab/stigmergylive/logs/ChannelLogger/freenode/#*/*

cat $LOGS | grep "<Utopiah" | sed -e "s/[^a-zA-Z]/ /g" | sed -e "s/ /\n/g" | sed -e "s/^.\{1,3\}$//" |sort | uniq

# cleaning by removing low frequency words
# ... | sed -e "s/[^a-zA-Z]/ /g" | sed -e "s/ /\n/g" | sed -e "s/^.\{1,3\}$//" |sort | uniq -c | grep -v " 1" | grep -v " 2" | grep -v " 3" | wc -l

# 10 most commonly used words
# ... | sed -e "s/[^a-zA-Z]/ /g" | sed -e "s/ /\n/g" | sed -e "s/^.\{1,3\}$//" |sort | uniq -c | sort -n | tail -15