#!/usr/bin/env perl -l

use strict;
use warnings;

use XML::LibXML;

my $xml_file = 'pm_1149767_xml_parse.xml';
my $parser = XML::LibXML::->new();
my $doc = $parser->load_xml(location => $xml_file);
my $re = qr{%([^%]+)%};

for ($doc->findnodes('//span/text()')) {
    print $1 while /$re/g;
}

##</code><code>##

<span ...>%var%</span>

##</code><code>##

<span ...>
    %var%
</span>

##</code><code>##

<root>
    <A>
        <span color="#231f20" whatever="%DoNotMatch%" textOverprint="false">%PN1%</span>
        <span color="#231f20" whatever="%DoNotMatch%" textOverprint="false">
            %PN2%
        </span>
    </A>
    <B>
        <C>
            <span color="#231f20" textOverprint="false">%DIMMM%%DIMINCH%</span>
            <span color="#231f20" textOverprint="false">
                %DIMMM%
                %DIMINCH%
            </span>
            <span color="#231f20" textOverprint="false">%DIMMM%garbage%DIMINCH%</span>
            <span color="#231f20" textOverprint="false">%DIMMM%%%DIMINCH%</span>
            <span color="#231f20" textOverprint="false">%DIMMM%%%%DIMINCH%</span>
        </C>
    </B>
</root>

##</code><code>##

PN1
PN2
DIMMM
DIMINCH
DIMMM
DIMINCH
DIMMM
DIMINCH
DIMMM
DIMINCH
DIMMM
DIMINCH

##</code><code>##

for my $context ($doc->findnodes('//span')) {
    print $context;
    for my $text ($context->findnodes('text()')) {
        print $text;
        while ($text =~ /$re/g) {
            print $1;
        }
    }
}

##</code><code>##

<span color="#231f20" whatever="%DoNotMatch%" textOverprint="false">%PN1%</span>
%PN1%
PN1
<span color="#231f20" whatever="%DoNotMatch%" textOverprint="false">
            %PN2%
        </span>

            %PN2%
        
PN2
<span color="#231f20" textOverprint="false">%DIMMM%%DIMINCH%</span>
%DIMMM%%DIMINCH%
DIMMM
DIMINCH
<span color="#231f20" textOverprint="false">
                %DIMMM%
                %DIMINCH%
            </span>

                %DIMMM%
                %DIMINCH%
            
DIMMM
DIMINCH
<span color="#231f20" textOverprint="false">%DIMMM%garbage%DIMINCH%</span>
%DIMMM%garbage%DIMINCH%
DIMMM
DIMINCH
<span color="#231f20" textOverprint="false">%DIMMM%%%DIMINCH%</span>
%DIMMM%%%DIMINCH%
DIMMM
DIMINCH
<span color="#231f20" textOverprint="false">%DIMMM%%%%DIMINCH%</span>
%DIMMM%%%%DIMINCH%
DIMMM
DIMINCH