You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spamassassin.apache.org by jm...@apache.org on 2007/07/24 15:26:57 UTC

svn commit: r559048 - /spamassassin/trunk/masses/rule-dev/seek-phrases-in-log

Author: jm
Date: Tue Jul 24 06:26:56 2007
New Revision: 559048

URL: http://svn.apache.org/viewvc?view=rev&rev=559048
Log:
oops, fix --ruleprefix too

Modified:
    spamassassin/trunk/masses/rule-dev/seek-phrases-in-log

Modified: spamassassin/trunk/masses/rule-dev/seek-phrases-in-log
URL: http://svn.apache.org/viewvc/spamassassin/trunk/masses/rule-dev/seek-phrases-in-log?view=diff&rev=559048&r1=559047&r2=559048
==============================================================================
--- spamassassin/trunk/masses/rule-dev/seek-phrases-in-log (original)
+++ spamassassin/trunk/masses/rule-dev/seek-phrases-in-log Tue Jul 24 06:26:56 2007
@@ -56,7 +56,7 @@
 my @files = ();
 GetOptions(
         "rules" => \$opt{rules},
-        "ruleprefix" => \$opt{ruleprefix},
+        "ruleprefix=s" => \$opt{ruleprefix},
         "reqhitrate=s" => \$opt{reqhitrate},
         "reqpatlength=s" => \$opt{reqpatlength},
         "maxtextread=s" => \$opt{maxtextread},
@@ -149,16 +149,16 @@
 }
 
 sub discard_hapaxes {
-  my $killed = 0;
+  my $before = (scalar keys %ngram_count);
   foreach my $tok (keys %ngram_count) {
     if ($ngram_count{$tok} == 1) {
       delete $ngram_count{$tok};
       delete $msg_subset_hit{$tok};
-      $killed++;
     }
   }
-  warn "shrunk dbs: $killed hapaxes killed, kept ".
-                    (scalar keys %ngram_count)." entries\n";
+  my $after = (scalar keys %ngram_count);
+  my $killed = ($after - $before);
+  warn "shrunk dbs: $killed hapaxes killed, kept $after entries\n";
 }
 
 sub proc_text_ham {