unable to parse xml file using registered namespace

Question

I am using XML::LibXML to parse a XML file. There seems to some problem in using registered namespace while accessing the node elements. I am planning to covert this xml data into CSV file. I am trying to access each and every element here. To start with I tried out extracting attribute values of <country> and <state> tags. Below is the code I have come with . But I am getting error saying XPath error : Undefined namespace prefix.

use strict;
use warnings;
use Data::Dumper;
use XML::LibXML;

my $XML=<<EOF;
<DataSet xmlns="http://www.w3schools.com" xmlns:xsi="https://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.w3schools.com note.xsd">
    <exec>
        <survey_region ver="1.1" type="x789" date="20160312"/>
        <survey_loc ver="1.1" type="x789" date="20160312"/>
        <note>Population survey</note>
    </exec>
    <country name="ABC" type="MALE">
        <state name="ABC_state1" result="PASS">
            <info>
                <type>literacy rate comparison</type>
            </info>
            <comment><![CDATA[
Some random text
contained here
]]></comment>
        </state>
    </country>
    <country name="XYZ" type="MALE">
        <state name="XYZ_state2" result="FAIL">
            <info>
                <type>literacy rate comparison</type>
            </info>
            <comment><![CDATA[
any random text data
]]></comment>
        </state>
    </country>
</DataSet>
EOF




my $parser = XML::LibXML->new();
my $doc  = $parser->parse_string($XML);


my $xc     = XML::LibXML::XPathContext->new($doc);
$xc->registerNs('x','http://www.w3schools.com');



foreach my $camelid ($xc->findnodes('//x:DataSet')) {

    my $country_name = $camelid->findvalue('./x:country/@name');
    my $country_type = $camelid->findvalue('./x:country/@type');

    my $state_name =  $camelid->findvalue('./x:state/@name');
    my $state_result =  $camelid->findvalue('./x:state/@result');
    print "state_name ($state_name)\n";
    print "state_result ($state_result)\n";
    print "country_name ($country_name)\n";
    print "country_type ($country_type)\n";
}

Update if I remove the name space from XML and change my XPath slightly it seems to work. Can someone help me understand the difference.

foreach my $camelid ($xc->findnodes('//DataSet')) {
    my $country_name = $camelid->findvalue('./country/@name');
    my $country_type = $camelid->findvalue('./country/@type');

    my $state_name =  $camelid->findvalue('./country/state/@name');
    my $state_result =  $camelid->findvalue('./country/state/@result');
    print "state_name ($state_name)\n";
    print "state_result ($state_result)\n";
    print "country_name ($country_name)\n";
    print "country_type ($country_type)\n";
}

Answer 1

This would be my approach

#!/usr/bin/perl

use strict;
use warnings;
use XML::LibXML;

my $XML=<<EOF;
<DataSet xmlns="http://www.w3schools.com" xmlns:xsi="https://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.w3schools.com note.xsd">
    <exec>
        <survey_region ver="1.1" type="x789" date="20160312"/>
        <survey_loc ver="1.1" type="x789" date="20160312"/>
        <note>Population survey</note>
    </exec>
    <country name="ABC" type="MALE">
        <state name="ABC_state1" result="PASS">
            <info>
                <type>literacy rate comparison</type>
            </info>
            <comment><![CDATA[
Some random text
contained here
]]></comment>
        </state>
    </country>
    <country name="XYZ" type="MALE">
        <state name="XYZ_state2" result="FAIL">
            <info>
                <type>literacy rate comparison</type>
            </info>
            <comment><![CDATA[
any random text data
]]></comment>
        </state>
    </country>
</DataSet>
EOF


my $parser = XML::LibXML->new();
my $tree = $parser->parse_string($XML);
my $root = $tree->getDocumentElement;
my @country = $root->getElementsByTagName('country');


foreach my $citem(@country){
    my $country_name = $citem->getAttribute('name');
    my $country_type = $citem->getAttribute('type');
    print "Country Name -- $country_name\nCountry Type -- $country_type\n";
    my @state = $citem->getElementsByTagName('state');
    foreach my $sitem(@state){
        my @info = $sitem->getElementsByTagName('info');
        my $state_name = $sitem->getAttribute('name');
        my $state_result = $sitem->getAttribute('result');
        print "State Name -- $state_name\nState Result -- $state_result\n";
        foreach my $i (@info){
            my $text = $i->getElementsByTagName('type');
            print "Info --- $text\n";
        }
    }
    print "\n";
}

Of course you can manipulate the data anyway you'd like. If you are parsing from a file change parse_string to parse_file.

For the individual elements in the xml use the getElementsByTagName to get the elements within the tags. This should be enough to get you going