01: use strict; 02: use File::Find; 03: use HTML::TokeParser; 04: 05: my $bak_ext = '.bak'; 06: my $root_dir = '/temp'; 07: 08: find(\&wanted, $root_dir); 09: 10: sub wanted { 11: # if the extension fits... 12: if ( /\.html?$/i ) { 13: print "Processing $_\n"; 14: my $new = $_; 15: my $bak = $_ . $bak_ext; 16: rename $_, $bak or die "Cannot rename $_ to $bak: $!"; 17: 18: open NEW, "> $new" or die "Cannot open $new for writing: $!"; 19: + #WHAT IS THE + DOING? 20: #I DONT UNDERSTAND THIS TOKEN PART 21: my $p = HTML::TokeParser->new( $bak ); #IS new( $bak ) A FUNCTION 22: # AND IF SO WHAT IS IT DOING? 23: while ( my $token = $p->get_token ) { 24: 25: # this index is the 'raw text' of the token 26: #I AM LOST ON THIS PART ALTHOUGH I UNDERSTAND IT IS 27: #AN IF ELSE STATEMENT WHAT IS THE 'T' AND 1 AND -1 DOING?? 28: my $text_index = $token->[0] eq 'T' ? 1 : -1; 29: 30: # it's both a start tag and a meta tag 31: #PLEASE EXPLAIN THIS PART 32: if ( $token->[0] eq 'S' and $token->[1] eq 'meta' ) { 33: $token->[ $text_index ] =~ s/AA\.//g; 34: } 35: #I DONT UNDERSTAND THIS PART. 36: print NEW $token->[ $text_index ]; 37: } 38: close NEW; 39: } else { 40: print "Skipping $_\n"; 41: } 42: } ##

##



<
    input
    type="hidden"
    name="weird indenting is legal"
    value=???
>



##

##

28:              my $text_index = $token->[0] eq 'T' ? 1 : -1;

##

##

  ["S",  $tag, $attr, $attrseq, $text]
  ["E",  $tag, $text]
  ["T",  $text, $is_data]
  ["C",  $text]
  ["D",  $text]
  ["PI", $token0, $text]

##

##

[
  'S',
  'meta',
  {
    'content' => 'Web data ',
    'name' => 'doc'
  },
  [
    'name',
    'content'
  ],
  ''
];

##

##

32:              if ( $token->[0] eq 'S' and $token->[1] eq 'meta' )    {
33:                  $token->[ $text_index ] =~ s/AA\.//g;
34:              }