home *** CD-ROM | disk | FTP | other *** search
/ OS/2 Shareware BBS: 22 gnu / 22-gnu.zip / gnuawk.zip / awklib / eg / prog / wordfreq.awk < prev   
Text File  |  1997-03-15  |  316b  |  14 lines

  1. # Print list of word frequencies
  2. {
  3.     $0 = tolower($0)    # remove case distinctions
  4.     gsub(/[^a-z0-9_ \t]/, "", $0)  # remove punctuation
  5.     for (i = 1; i <= NF; i++)
  6.         freq[$i]++
  7. }
  8. END {
  9.     sort = "sort +1 -nr"
  10.     for (word in freq)
  11.         printf "%s\t%d\n", word, freq[word] | sort
  12.     close(sort)
  13. }
  14.