use strict;
use warnings;
use XML::LibXML::Reader qw( :types );
sub new {
my $class = shift;
return bless({
reader => XML::LibXML::Reader->new(@_),
elem_depth => 0,
buf => '',
}, $class);
}
sub get_next {
my ($self) = @_;
my $reader = $self->{reader};
for (;;) {
return () if $reader->read() != 1;
if ($reader->nodeType() == XML_READER_TYPE_TEXT) {
if ($self->{elem_depth} && $reader->depth() == $self->{elem_d
+epth} + 1) {
$self->{buf} .= $reader->value();
}
}
elsif ($reader->nodeType() == XML_READER_TYPE_ELEMENT) {
if ($reader->name() eq 'elem') {
$self->{elem_depth} = $reader->depth();
}
}
elsif ($reader->nodeType() == XML_READER_TYPE_END_ELEMENT) {
if ($reader->name() eq 'elem') {
return substr($self->{buf}, 0, length($self->{buf}), '');
}
}
}
}
{
my $reader1 = __PACKAGE__->new(location => "file1.xml");
my $reader2 = __PACKAGE__->new(location => "file2.xml");
for (;;) {
my $text1 = $reader1->get_next();
my $text2 = $reader2->get_next();
last if !defined($text1) && !defined($text2);
die if !defined($text1);
die if !defined($text2);
process_data($text1, $text2);
}
}
Assumes all elem elements are "interesting" ones, not just the ones found under the root. Easy to change, though.
Output left to the user. May I suggest XML::Writer since it keeps next to nothing in memory.