#!/bin/perl -w
use strict;

use XML::Twig;

# create the regexp for date, this should be improved
my $month = qr/(?:(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\.?)/;
my $day   = qr/(?:(?:[0-2]?[0-9]|30|31)(?:st|nd|th)?)/;
my $year  = qr/(?:,?\s*\d+)?/;

my $date= qr/($month $day$year)/;

# this could probably be improved too!
my $number= qr/(\d{2,})/;

while( <DATA>)
  { chomp;
    # create the un-tagged XML
    my $t= XML::Twig->new();
      # XML::Parser::Expat:::xml_escape just replaces & by &amp;, 
      # > by &lt; etc... 
       $t->parse( "<mytxt>". XML::Parser::Expat:::xml_escape( 1, $_)  . "</mytxt>");

    # mark the dates
    $t->root->mark( $date, 'date');

    # mark the numbers,
    foreach my $elt ($t->descendants( '#PCDATA'))
      { #skip if in date
        next if( $elt->in_context( 'date'));
        $elt->mark( $number, 'number');
      }

    # output
    $t->print;
    print "\n";
  }


__DATA__
On Oct. 21, the Dow Jones rose to 10043 points
On May 1st 2001, 12 people were working in France