summaryrefslogtreecommitdiffstats
path: root/contrib/awk/awklib/eg/prog/wordfreq.awk
diff options
context:
space:
mode:
Diffstat (limited to 'contrib/awk/awklib/eg/prog/wordfreq.awk')
-rw-r--r--contrib/awk/awklib/eg/prog/wordfreq.awk13
1 files changed, 13 insertions, 0 deletions
diff --git a/contrib/awk/awklib/eg/prog/wordfreq.awk b/contrib/awk/awklib/eg/prog/wordfreq.awk
new file mode 100644
index 0000000..b67fed4
--- /dev/null
+++ b/contrib/awk/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)
+}
OpenPOWER on IntegriCloud