xmltv/grab/pt tv_grab_pt,1.50,1.51

Update of /cvsroot/xmltv/xmltv/grab/pt
In directory sfp-cvs-1.v30.ch3.sourceforge.com:/tmp/cvs-serv2637

Modified Files:
	tv_grab_pt 
Log Message:
(minor) fix badutf8 error

Index: tv_grab_pt
===================================================================
RCS file: /cvsroot/xmltv/xmltv/grab/pt/tv_grab_pt,v
retrieving revision 1.50
retrieving revision 1.51
diff -C2 -d -r1.50 -r1.51
*** tv_grab_pt	7 May 2014 16:24:33 -0000	1.50
--- tv_grab_pt	8 May 2014 12:39:52 -0000	1.51
***************
*** 163,166 ****
--- 163,167 ----
      Verbose  => $opt_debug,
  } );
+ ##$XMLTV::Get_nice::Delay = 0 if $opt_debug;
  
  XMLTV::Ask::init($opt_gui);
***************
*** 376,383 ****
          my $uref = new Unicode::UTF8simple; 
       
!         *toUTF8 = sub { return $uref->toUTF8(@_); } 
      } else { 
          #   *toUTF8 = sub { my $str = $_[1]; Encode::from_to($str, $_[0], "utf-8"); return $str; } 
!         *toUTF8 = sub { return Encode::encode("utf-8", $_[0]); } 
      }
  }
--- 377,384 ----
          my $uref = new Unicode::UTF8simple; 
       
!         *toUTF8 = sub { return fix_utf8( $uref->toUTF8(@_) ); } 
      } else { 
          #   *toUTF8 = sub { my $str = $_[1]; Encode::from_to($str, $_[0], "utf-8"); return $str; } 
!         *toUTF8 = sub { return fix_utf8( Encode::encode("utf-8", $_[0]) ); } 
      }
  }
***************
*** 403,406 ****
--- 404,424 ----
  }
  
+ # UTF-8 fixups.
+ sub fix_utf8( $ ) {
+     #  The details page claims to be utf-8 but there are some invalid characters in the incoming data
+     #  e.g. it claims en-dash as C2 96 (which is a control code in utf-8!)
+     #  Looks like an improper conversion from Windows-1252 in the source data
+     #
+     return $_[0] if !defined $_[0];
+     $_[0] =~ s/\xC2\x96/\xE2\x80\x93/og;      # replace invalid en-dash with correct value
+     $_[0] =~ s/\xC2\x80/\xE2\x82\xAC/og;      # euro
+     $_[0] =~ s/\xC2\x85/\xE2\x80\xA6/og;      # ellipsis
+     $_[0] =~ s/\xC2\x92/\xE2\x80\x99/og;      # apostrophe
+     $_[0] =~ s/\xC2\x93/\xE2\x80\x9C/og;      # open double quote
+     $_[0] =~ s/\xC2\x94/\xE2\x80\x9D/og;      # close double quote
+     $_[0] =~ s/\xC2[\x80-\x9F]//og;           # dump the rest
+     return $_[0];
+ }
+ 
  # Remove leading & trailing spaces
  sub trim( $ ) {
***************
*** 639,643 ****
  	# We could check the title matches what we already have but why not just trust the 'id' is correct ;-)
  	
! 	$$prog{'desc'} = $data[1];		# store the description in our prog hash
  	$$prog{'icon'} = "http://images.$DOMAIN/" . $data[2];		# [2] is a uri to the programme image
  
--- 657,661 ----
  	# We could check the title matches what we already have but why not just trust the 'id' is correct ;-)
  	
! 	$$prog{'desc'} = tidy $data[1];		# store the description in our prog hash
  	$$prog{'icon'} = "http://images.$DOMAIN/" . $data[2];		# [2] is a uri to the programme image
  


------------------------------------------------------------------------------
Is your legacy SCM system holding you back? Join Perforce May 7 to find out:
• 3 signs your SCM is hindering your productivity
• Requirements for releasing software faster
• Expert tips and advice for migrating your SCM now
http://p.sf.net/sfu/perforce