UsefulUserName UsefulUserName - 4 months ago 76
Perl Question

Perl: Inserting an XML::Twig node with XML::Twig

I am comparing two XML files. If I find a node missing in one of the files I want to insert it into the other file. Here is how I have been trying it:

my $out_file = 'fbCI_report.xml';
open my $fh_out, '>>', $out_file or die "Can't open $out_file for writing: $!";

my $currentReport = XML::Twig->new( pretty_print => 'indented' );
$currentReport->parsefile($path_to_currentReport);
print "Loaded current report.\n";

my $newReport = XML::Twig->new( pretty_print => 'indented' );
$newReport->parsefile($path_to_newReport);
print "Loaded new report.\n";

my $currentRoot = $currentReport->root; # get the root
my $currentBuilds = $currentRoot->first_child(); # get the builds node
my $currentXCR = $currentBuilds->first_child(); # get the xcr node

my $newRoot = $newReport->root; # get the root
my $newBuilds = $newRoot->first_child(); # get the builds node
my $newXCR = $newBuilds->first_child(); # get the xcr node

my @currentXCRarray = $currentBuilds->children('xcr');
my @newXCRarray = $newBuilds->children('xcr');
my $numberOfxcr = $newBuilds->children_count();

foreach my $currentXCRmod ( @currentXCRarray ) {

my $currentID = $currentXCRmod->att("id");

foreach my $newXCRmod (@newXCRarray) {

my $newID = $newXCRmod->att("id");

if ( $newID == $currentID ) {
last;
}
elsif ( $count == $numberOfxcr && $newID != $currentID ) {
my $insert = $currentBuilds->insert_new_elt($newXCRmod);
print "XCR does not exist in current report, adding it..\n";
}

$count++;
}
}

print $fh_out $currentReport->sprint();
close $fh_out;


However this does not insert the node with the corresponding children but what I guess is the reference to the node:
<XML::Twig::Elt=HASH(0x326efe0)/>
. Is there a way to insert the node properly? I have yet to find anything on the CPAN site.

Sample data, current.xml:

<project>
<builds>
<xcr id="13367" buildable="false">
<artifact name="rb"/>
<artifact name="syca"/>
</xcr>
<xcr id="13826" buildable="false">
<artifact name="dcs"/>
</xcr>
<\builds>
<\project>


new.xml:

<project>
<builds>
<xcr id="13367" buildable="false">
<artifact name="rb"/>
<artifact name="syca"/>
</xcr>
<xcr id="13826" buildable="false">
<artifact name="dcs"/>
</xcr>
<xcr id="10867" buildable="true">
<artifact name="smth"/>
<artifact name="top"/>
<artifact name="tree"/>
</xcr>
<\builds>
<\project>

Answer

You're right - that's the stringified text of an XML::Twig::Elt.

The problem is - insert_new_elt creates a new element. So what you're doing is effectively, "printing" the element id ( XML::Twig::Elt=HASH(0x326efe0)) and creating a new node called that.

But you don't want to do that - you're wanting to copy an existing one.

So I would suggest what you want to do is:

my $copied_elt = $currentXCRmod -> copy;
$copied_elt -> paste ( last_child => $currentBuilds );

Which will transfer the element (into the 'last_child' position).

Although I'd suggest that your loop is perhaps something you could improve on too - I would suggest you look at a twig_handler, to check which ID's exist in the file at parse:

my %seen_id; 
sub collect_ids {
   my ( $twig, $element ) = @_;
   $seen_id { $element->att('id') } ++; 
} 

And then call this at parse time:

my $currentReport = XML::Twig->new(twig_handlers => { 'xcr' => \&collect_ids}, 
                                   pretty_print=>'indented');
$currentReport->parsefile($path_to_currentReport);

And this will let you easily compare/copy which ones do or don't exist.

Or alternatively (based on your XML sample so far):

#!/usr/bin/env perl

use strict;
use warnings 'all';

use Data::Dumper;
use XML::Twig;

my $current = XML::Twig -> new ( ) -> parsefile ('test1.xml');
my $new = XML::Twig -> new (  ) -> parsefile ( 'test2.xml'); 

my $cur_builds = $current -> root -> get_xpath('./builds',0);

foreach my $xcr ( $new -> findnodes('//xcr') ) {
   my $id = $xcr -> att('id'); 
   if ( not $current -> findnodes("//xcr[\@id=\"$id\"]") ) {
      print "$id not in current, copying\n"; 
      my $copy = $xcr -> copy; 
      $copy -> paste ( last_child => $cur_builds ); 
   }
}

$current -> set_pretty_print('indented_a');
$current -> print;
Comments