#!/usr/bin/perl
use strict;
use warnings;

my $tag;
my $output;
my $fh;
my $flag ='';
my $output_text;

while (<DATA>) {
    chomp;
    s/[\cA-\cZ]//g;
    s/\^[A-Z]//g;

        if(/^{(.*)}$/)     # match {METATAG} line
                {
                $fh = xml_output($output, $tag, $fh);
                $output = "";
                $tag = $1;
                }
                 else
                {            # not a {TAG} line
                next unless($tag);
                next if(/^\s*$/);
                $output .= ($output) ? " $_" : "<$tag>$_";
                }
        } # End of While Loop


$fh = xml_output($output, $tag, $fh);


if($fh) {
    print $fh "</ROOT>\n";
    close($fh);
}
exit(0);
# Subroutine to open the file with the filename as {TAG}


sub xml_output {
    my ($output, $tag, $fh) = @_;
    if($output) {
        if($output =~ m/<TAG>(.*)/) {
            if($fh) {
                print $fh "</ROOT>\n";
                close($fh);
            }
            open($fh, '>', "$1.xml") or die "$1.xml: $!";
            print $fh "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<RO
+OT>\n";
        }


               $output =~ s/\s*(?=(<.+>|<.+\/>|<\/.+>|<\/.+><.+>))//g;
               $output =~ s/\s*(?=<)//g;
               $output =~ s/(?<=>)\s*//g;
               $output =~ s/<br\/>/&lt;br\/&gt;/g;
               $output =~ s/\s*(?=(&lt;br\/&gt;)\s*)//g;
               $output =~ s/&lt;br\/&gt;\s*/&lt;br\/&gt;/g;
               $output =~ s/&lt;br\/&gt;$//g;
               print $fh "$output</$tag>\n";
             }
    return($fh);
  } # End of sub sroutine
__DATA__
020200001109VUTVS01 00004407B3^V^V^A2^C^D^V^V^A 0000 0001 050102 N S00
+00000000 00001444^B{IT}R
{DATE}
050102
{TDATE}
Sunday, January 02, 2005
{EDITION}
6
{TAG}
0412270403
{BODY}
Certified Financial Planner for DiStefano Finacial  Group in Westfield
+,
MA.
^C^D^V^V^A 0000 0002 050102 N S0000000000 00002158^B{IT}R
{DATE}
050102
{TDATE}
Sunday, January 02, 2005
{EDITION}
6
{PAGE}
H5
{TAG}
0412270405
{BODY}
Amdur - Rosenberg < Gabriela Rosenberg, the daughter of Anita and Samu
+el Rosenberg of Buenos

[download]
{IT} is the start of the file.
I have to split the files into many based on {IT} tag and filename with {TAG} value.
and all the contents are written in the file. file should be like for example: 0412270403.xml 
<?xml version="1.0" encoding="UTF-8"?>
<ROOT>
<IT>R</IT>
<DATE>050102</DATE>
<TDATE>Sunday, January 02, 2005</TDATE>
<EDITION>6</EDITION>
<TAG>0412270403</TAG>
<BODY>Certified Financial Planner for DiStefano Finacial  Group in Wes
+tfield,MA.</BODY>
</ROOT>

[download]

In reply to file split by Anonymous Monk

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post, it's "PerlMonks-approved HTML":


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.