diff options
| author | Arnold D. Robbins <arnold@skeeve.com> | 2010-07-16 12:41:09 +0300 |
|---|---|---|
| committer | Arnold D. Robbins <arnold@skeeve.com> | 2010-07-16 12:41:09 +0300 |
| commit | 8c042f99cc7465c86351d21331a129111b75345d (patch) | |
| tree | 9656e653be0e42e5469cec77635c20356de152c2 /awklib/eg/prog/wordfreq.awk | |
| parent | 8ceb5f934787eb7be5fb452fb39179df66119954 (diff) | |
| download | egawk-8c042f99cc7465c86351d21331a129111b75345d.tar.gz egawk-8c042f99cc7465c86351d21331a129111b75345d.tar.bz2 egawk-8c042f99cc7465c86351d21331a129111b75345d.zip | |
Move to gawk-3.0.0.
Diffstat (limited to 'awklib/eg/prog/wordfreq.awk')
| -rw-r--r-- | awklib/eg/prog/wordfreq.awk | 13 |
1 files changed, 13 insertions, 0 deletions
diff --git a/awklib/eg/prog/wordfreq.awk b/awklib/eg/prog/wordfreq.awk new file mode 100644 index 00000000..b67fed47 --- /dev/null +++ b/awklib/eg/prog/wordfreq.awk @@ -0,0 +1,13 @@ +# Print list of word frequencies +{ + $0 = tolower($0) # remove case distinctions + gsub(/[^a-z0-9_ \t]/, "", $0) # remove punctuation + for (i = 1; i <= NF; i++) + freq[$i]++ +} +END { + sort = "sort +1 -nr" + for (word in freq) + printf "%s\t%d\n", word, freq[word] | sort + close(sort) +} |