summaryrefslogtreecommitdiffstats
path: root/contrib/awk/awklib/eg/prog/wordfreq.awk
diff options
context:
space:
mode:
authorobrien <obrien@FreeBSD.org>2001-11-02 21:06:08 +0000
committerobrien <obrien@FreeBSD.org>2001-11-02 21:06:08 +0000
commitcfe0e2b488d886d14fc1755679b8a88165b22d92 (patch)
treefbf9ca4d3f276e13b39090465008b182d20f0e5a /contrib/awk/awklib/eg/prog/wordfreq.awk
parent9682ea287751aa7aad9e21c50ba74cfb3d7314d0 (diff)
parent223f0286ad0612783e0da01de3b5bfdc52e3b25c (diff)
downloadFreeBSD-src-cfe0e2b488d886d14fc1755679b8a88165b22d92.zip
FreeBSD-src-cfe0e2b488d886d14fc1755679b8a88165b22d92.tar.gz
This commit was generated by cvs2svn to compensate for changes in r85898,
which included commits to RCS files with non-trunk default branches.
Diffstat (limited to 'contrib/awk/awklib/eg/prog/wordfreq.awk')
-rw-r--r--contrib/awk/awklib/eg/prog/wordfreq.awk11
1 files changed, 9 insertions, 2 deletions
diff --git a/contrib/awk/awklib/eg/prog/wordfreq.awk b/contrib/awk/awklib/eg/prog/wordfreq.awk
index b67fed4..62db5cf 100644
--- a/contrib/awk/awklib/eg/prog/wordfreq.awk
+++ b/contrib/awk/awklib/eg/prog/wordfreq.awk
@@ -1,10 +1,17 @@
-# Print list of word frequencies
+# wordfreq.awk --- print list of word frequencies
+
{
$0 = tolower($0) # remove case distinctions
- gsub(/[^a-z0-9_ \t]/, "", $0) # remove punctuation
+ # remove punctuation
+ gsub(/[^[:alnum:]_[:blank:]]/, "", $0)
for (i = 1; i <= NF; i++)
freq[$i]++
}
+
+END {
+ for (word in freq)
+ printf "%s\t%d\n", word, freq[word]
+}
END {
sort = "sort +1 -nr"
for (word in freq)
OpenPOWER on IntegriCloud