X-Git-Url: http://dxcluster.net/gitweb/gitweb.cgi?p=spider.git;a=blobdiff_plain;f=perl%2FBadWords.pm;h=312a04082c705fac550f9b0fcb065388cca2e564;hp=141b3e9a729b6a933149cb0bf71bf4a942938285;hb=6ec22e78a4a344ce675645fabf18b2a1971f364a;hpb=53b251b7abcc15dd2f854b7e8c2e71a075e9969a diff --git a/perl/BadWords.pm b/perl/BadWords.pm index 141b3e9a..312a0408 100644 --- a/perl/BadWords.pm +++ b/perl/BadWords.pm @@ -19,41 +19,27 @@ use IO::File; use vars qw($badword $regexcode); -my $oldfn = localdata("badwords"); -my $regex = localdata("badw_regex"); -my $bwfn = localdata("badword"); - -# copy issue ones across -filecopy("$regex.gb.issue", $regex) unless -e $regex; -filecopy("$bwfn.issue", $bwfn) unless -e $bwfn; - -$badword = new DXHash "badword"; +our $regex; # load the badwords file sub load { + my $bwfn = localdata("badword"); + filecopy("$main::data.issue", $bwfn) unless -e $bwfn; + my @out; - my $fh = new IO::File $oldfn; + + $badword = new DXHash "badword"; - if ($fh) { - while (<$fh>) { - chomp; - next if /^\s*\#/; - my @list = split " "; - for (@list) { - $badword->add($_); - } - } - $fh->close; - $badword->put; - unlink $oldfn; - } push @out, create_regex(); return @out; } sub create_regex { + $regex = localdata("badw_regex"); + filecopy("$regex.gb.issue", $regex) unless -e $regex; + my @out; my $fh = new IO::File $regex; @@ -69,7 +55,7 @@ sub create_regex my $w = uc $_; my @l = split //, $w; my $e = join '+[\s\W]*', @l; - $s .= "push \@out, \$1 if \$str =~ /\\b($e)/;\n"; + $s .= qq{push \@out, \$1 if \$str =~ m|\\b($e+)|;\n}; } } $s .= "return \@out;\n}";