# wordfreq.awk --- print list of word frequencies
# from http://www.sunsite.ualberta.ca/Documentation/Gnu/gawk-3.1.0/html_chapter/gawk_15.html#SEC220

{
    $0 = tolower($0)    # remove case distinctions
    # remove punctuation
    gsub(/[^[:alnum:]_[:blank:]]/, "", $0)
    for (i = 1; i <= NF; i++)
        freq[$i]++
}

END {
    for (word in freq)
        printf "%-20s\t%4d\n", word, freq[word]
}