diff options
Diffstat (limited to 'awklib/eg/prog/dupword.awk')
-rw-r--r-- | awklib/eg/prog/dupword.awk | 9 |
1 files changed, 7 insertions, 2 deletions
diff --git a/awklib/eg/prog/dupword.awk b/awklib/eg/prog/dupword.awk index 9a518a16..a2cc7d2b 100644 --- a/awklib/eg/prog/dupword.awk +++ b/awklib/eg/prog/dupword.awk @@ -1,10 +1,15 @@ -# dupword --- find duplicate words in text +# dupword.awk --- find duplicate words in text +# # Arnold Robbins, arnold@gnu.org, Public Domain # December 1991 +# Revised October 2000 { $0 = tolower($0) - gsub(/[^A-Za-z0-9 \t]/, ""); + gsub(/[^[:alnum:][:blank:]]/, " "); + $0 = $0 # re-split + if (NF == 0) + next if ($1 == prev) printf("%s:%d: duplicate %s\n", FILENAME, FNR, $1) |