user-tools/htmlentities

   1 #!/usr/bin/env perl
   2
   3 use HTML::Entities;
   4 use utf8;
   5 use Getopt::Long;
   6
   7 $unsafe_control = 1;
   8 $unsafe_meta = 1;
   9 $unsafe_highbit = 1;
  10
  11 GetOptions(
  12  'control!' => \$unsafe_control,
  13  'meta!' => \$unsafe_meta,
  14  'highbit!' => \$unsafe_highbit,
  15 ) or die "Usage: $0 [--[no-]control] [--[no-]meta] [--[no-]highbit]\n";
  16
  17 $unsafe_chars = '';
  18
  19 if($unsafe_control) {
  20         $unsafe_chars .= "\x00-\x08\x11\x12\x14-\x1F";
  21 }
  22 if($unsafe_meta) {
  23         $unsafe_chars .= "><&\"'";
  24 }
  25 if($unsafe_highbit) {
  26         $unsafe_chars .= "\x7F-\x{FFFFFFFF}";
  27 }
  28
  29 binmode STDIN, ":utf8";
  30 binmode STDOUT, ":utf8";
  31 while(<>)
  32 {
  33         print encode_entities($_, $unsafe_chars);
  34 }
  35
  36 __END__
  37
  38 =pod
  39
  40 =head1 NAME
  41
  42 htmlentities - Convert plain text into HTML-safe text
  43
  44 =head1 OPTIONS
  45
  46 =over 4
  47
  48 =item --[no-]control
  49
  50 escape control chars (0x00-0x1F except TAB, LF, and CR)
  51
  52 =item --[no-]meta
  53
  54 escape meta chars (less-than, greater-than, ampersand, double- and single-quote)
  55
  56 =item --[no-]highbit
  57
  58 scape non-ASCII chars
  59
  60 =back
  61
  62 =cut
  63