[popfile-commit] engine/Classifier MailParse.pm,1.131,1.132

[<jgr...@us...>]

Update of /cvsroot/popfile/engine/Classifier
In directory sc8-pr-cvs1:/tmp/cvs-serv21196/Classifier

Modified Files:
	MailParse.pm 
Log Message:
Prevent duplicate call to add_url when parsing img tags, prevent spaces in charset decodes

Index: MailParse.pm
===================================================================
RCS file: /cvsroot/popfile/engine/Classifier/MailParse.pm,v
retrieving revision 1.131
retrieving revision 1.132
diff -C2 -d -r1.131 -r1.132
*** MailParse.pm	29 May 2003 10:49:06 -0000	1.131
--- MailParse.pm	9 Jun 2003 18:33:36 -0000	1.132
***************
*** 447,450 ****
--- 447,452 ----
          	    }
                  }
+ 
+                 next;
              }
  
***************
*** 536,540 ****
  
          if ( ( $attribute =~ /^content$/i ) && ( $tag =~ /^meta$/i ) ) {
!             if ( $value=~ /charset=(.{1,40})[\"\>]?/ ) {
                  update_word( $self, $1, $encoded, '', '', '' );
              }
--- 538,542 ----
  
          if ( ( $attribute =~ /^content$/i ) && ( $tag =~ /^meta$/i ) ) {
!             if ( $value=~ /charset=([^ ]{1,40})[\"\>]?/ ) {
                  update_word( $self, $1, $encoded, '', '', '' );
              }
***************
*** 621,624 ****
--- 623,628 ----
      $authinfo = $1 if ( $url =~ s/^(([[:alpha:]0-9\-_\.\;\:\&\=\+\$\,]+)(\@|\%40))+// );
  
+     $self->update_pseudoword( 'html', 'authorization', $encoded, $oldurl ) if ( defined( $authinfo ) && ( $authinfo ne '' ) );
+ 
      if ( $url =~ s/^(([[:alpha:]0-9\-_]+\.)+)(com|edu|gov|int|mil|net|org|aero|biz|coop|info|museum|name|pro|[[:alpha:]]{2})([^[:alpha:]0-9\-_\.]|$)/$4/i ) {
          $host = "$1$3";
***************
*** 1021,1025 ****
              # Look for =?foo? syntax that identifies a charset
  
!             if ( $line =~ /=\?(.{1,40})\?/ ) {
                  update_word( $self, $1, 0, '', '', 'charset' );
              }
--- 1025,1029 ----
              # Look for =?foo? syntax that identifies a charset
  
!             if ( $line =~ /=\?([^ ]{1,40})\?/ ) {
                  update_word( $self, $1, 0, '', '', 'charset' );
              }
***************
*** 1192,1196 ****
      # Check the encoding type in all RFC 2047 encoded headers
  
!     if ( $argument =~ /=\?(.{1,40})\?(Q|B)/i ) {
              update_word( $self, $1, 0, '', '', 'charset' );
      }
--- 1196,1200 ----
      # Check the encoding type in all RFC 2047 encoded headers
  
!     if ( $argument =~ /=\?([^ ]{1,40})\?(Q|B)/i ) {
              update_word( $self, $1, 0, '', '', 'charset' );
      }
***************
*** 1215,1219 ****
          $argument = $self->decode_string( $argument );
  
!         if ( $argument =~ /=\?(.{1,40})\?/ ) {
              update_word( $self, $1, 0, '', '', 'charset' );
          }
--- 1219,1223 ----
          $argument = $self->decode_string( $argument );
  
!         if ( $argument =~ /=\?([^ ]{1,40})\?/ ) {
              update_word( $self, $1, 0, '', '', 'charset' );
          }
***************
*** 1260,1264 ****
  
      if ( $header =~ /^Content-Type$/i ) {
!         if ( $argument =~ /charset=\"?([^\"]{1,40})\"?/ ) {
              update_word( $self, $1, 0, '' , '', 'charset' );
          }
--- 1264,1268 ----
  
      if ( $header =~ /^Content-Type$/i ) {
!         if ( $argument =~ /charset=\"?([^\" ]{1,40})\"?/ ) {
              update_word( $self, $1, 0, '' , '', 'charset' );
          }