Beefy Boxes and Bandwidth Generously Provided by pair Networks
The stupid question is the question not asked
 
PerlMonks  

Re^3: Processing Two XML Files in Parallel

by ikegami (Patriarch)
on Jul 25, 2011 at 23:16 UTC ( [id://916635]=note: print w/replies, xml ) Need Help??


in reply to Re^2: Processing Two XML Files in Parallel
in thread Processing Two XML Files in Parallel

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.

Log In?
Username:
Password:

What's my password?
Create A New User
Domain Nodelet?
Node Status?
node history
Node Type: note [id://916635]
help
Chatterbox?
and the web crawler heard nothing...

How do I use this?Last hourOther CB clients
Other Users?
Others chanting in the Monastery: (4)
As of 2024-03-29 15:41 GMT
Sections?
Information?
Find Nodes?
Leftovers?
    Voting Booth?

    No recent polls found