X-Git-Url: http://www.dxcluster.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=perl%2FAnnTalk.pm;h=f6b4653d28d497b9a854de43a206dc470eb86a58;hb=99077d96c91df307092394bf1028212adeec4c37;hp=72abfeb283c6bf35b6dbb839f999e3bf96259289;hpb=c23f49862b7a8c377daf9205b219cb327608c4da;p=spider.git diff --git a/perl/AnnTalk.pm b/perl/AnnTalk.pm index 72abfeb2..f6b4653d 100644 --- a/perl/AnnTalk.pm +++ b/perl/AnnTalk.pm @@ -17,8 +17,8 @@ use DXVars; use vars qw(%dup $duplth $dupage $filterdef); -$duplth = 60; # the length of text to use in the deduping -$dupage = 5*3600; # the length of time to hold spot dups +$duplth = 30; # the length of text to use in the deduping +$dupage = 5*3600; # the length of time to hold ann dups $filterdef = bless ([ # tag, sort, field, priv, special parser ['by', 'c', 0], @@ -47,8 +47,7 @@ sub dup chomp $text; unpad($text); $text =~ s/\%([0-9A-F][0-9A-F])/chr(hex($1))/eg; - $text = Encode::encode("iso-8859-1", $text) if $main::can_encode && Encode::is_utf8($text, 1); - $text = pack("C*", map {$_ & 127} unpack("C*", $text)); +# $text = Encode::encode("iso-8859-1", $text) if $main::can_encode && Encode::is_utf8($text, 1); $text =~ s/[^\#a-zA-Z0-9]//g; $text = substr($text, 0, $duplth) if length $text > $duplth; my $dupkey = "A$call|$to|\L$text";