XML::Rules 0.18

XML::Rules is a Perl module that can parse XML & process tags by rules starting from leaves.

SYNOPSIS

use XML::Rules;

$xml = < < *END*
< doc >
< person >
< fname >...< /fname >
< lname >...< /lname >
< email >...< /email >
< address >
< street >...< /street >
< city >...< /city >
< country >...< /country >
< bogus >...< /bogus >
< /address >
< phones >
< phone type="home" >123-456-7890< /phone >
< phone type="office" >663-486-7890< /phone >
< phone type="fax" >663-486-7000< /phone >
< /phones >
< /person >
< person >
< fname >...< /fname >
< lname >...< /lname >
< email >...< /email >
< address >
< street >...< /street >
< city >...< /city >
< country >...< /country >
< bogus >...< /bogus >
< /address >
< phones >
< phone type="office" >663-486-7891< /phone >
< /phones >
< /person >
< /doc >
*END*

@rules = (
_default = > sub {$_[0] = > $_[1]- >{_content}},
# by default Im only interested in the content of the tag, not the attributes
bogus = > undef,
# lets ignore this tag and all inner ones as well
address = > sub {address = > "$_[1]- >{street}, $_[1]- >{city} ($_[1]- >{country})"},
# merge the address into a single string
phone = > sub {$_[1]- >{type} = > $_[1]- >{content}},
# lets use the "type" attribute as the key and the content as the value
phones = > sub {delete $_[1]- >{_content}; %{$_[1]}},
# remove the text content and pass along the type = > content from the child nodes
person = > sub { # lets print the values, all the data is readily available in the attributes
print "$_[1]- >{lname}, $_[1]- >{fname} < $_[1]- >{email} >n";
print "Home phone: $_[1]- >{home}n" if $_[1]- >{home};
print "Office phone: $_[1]- >{office}n" if $_[1]- >{office};
print "Fax: $_[1]- >{fax}n" if $_[1]- >{fax};
print "$_[1]- >{address}nn";
return; # the < person > tag is processed, no need to remember what it contained
},
);
$parser = XML::Rules- >new(rules = > @rules);
$parser- >parse( $xml);