#!/bin/perl -w
use strict;

# 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,})/;

my %replace;
my $i=0;

while( <DATA>)
  { chomp;
    # entitize special characters, those 2 are sufficient here
    s{&}{&amp;}g;
    s{<}{&lt;}g;
    s{(?!<&)$date}  {$i++; $replace{$i}="<date>$1</date>"; "&$i;"}eg;     # replace the dates
    s{(?!<&)$number}{$i++; $replace{$i}="<number>$1</number>"; "&$i;"}eg; # replace the numbers 
    s{&(\d+);}{$replace{$1}}g;                                            # replace the &n;
    print "<mytext>$_</mytext>\n";
  }

__DATA__
On Oct. 21, the Dow Jones rose to 10043 points
On May 1st 2001, 12 people were working in France
On Nov. 20, I can still tell that 123 < 234