This commit is contained in:
20
ase/cmd/awk/wordfreq.awk
Normal file
20
ase/cmd/awk/wordfreq.awk
Normal file
@ -0,0 +1,20 @@
|
||||
# wordfreq.awk --- print list of word frequencies
|
||||
|
||||
{
|
||||
$0 = tolower($0); # remove case distinctions
|
||||
|
||||
# remove punctuation
|
||||
a=0;
|
||||
gsub(/[^[:alnum:]_[:blank:]]/, " ", $a);
|
||||
#gsub(/[^[:alnum:]_[:blank:]]/, " ");
|
||||
|
||||
for (i = 1; i <= NF; i++) freq[$i]++;
|
||||
}
|
||||
#/[^kkka-bcx-dd-y]|abc|def/
|
||||
|
||||
END {
|
||||
for (word in freq)
|
||||
print word, freq[word];
|
||||
}
|
||||
|
||||
|
Reference in New Issue
Block a user