So I have about 85 XML files that are 25-30mb each I am trying to process with XML::Twig. The problem is that I cannot seem to get XML::Twig to release the memory it consumes and my script quickly dies a bloated memory related death after a number of files. In a nutshell this is what I am doing. - Parse file using XML::Twig - Get just the IDs for each record - Lookup that ID in database and do some stuff - Process next record until end of XML file and repeat for next file. I threw it in debug and I can see the memory grow as each bit of XML is parsed. Can anyone see anything wrong with this code?

#!/usr/bin/perl -w
use strict;
use XML::Twig;
use DBI;
use DBD::Pg;
use SQL::Abstract;
use File::Copy;
use File::Basename;

my $inFile = 'data_100000_100500.xml';
if ( ! $inFile ) {
    die("No input file specified");
}
if ( ! -f $inFile ) {
    die("file '$inFile' not found");
}

my $dbname = "test";
my $user = "test";
my $password = "test";
my $host = "test03.server.com";
my $port = "5432";
my $dbh = DBI->connect("dbi:Pg:dbname=$dbname;host=$host;port=$port", 
+$user, $password, {AutoCommit => 0});
my $sql = SQL::Abstract->new(quote_char=>'"');
my @missing;
my @localmissing;
my $trust = 0;
my $localcount;
my $count;
my $sth;
my $fileStartID;
my $fileEndID;
my %BIOG;

process($inFile);

if (@missing) {
    open(MISSINGFILE, ">>missing.txt");
    foreach my $missing (@missing) {
        print MISSINGFILE $missing . "\n";
    }
    close MISSINGFILE;
    print "\nUNVERIFIED see missing.txt for missing records.\n";
} else {
    print "\nVerified 100%\n";
}
exit 0;

#
# Process the file
#
sub process {
    %BIOG = ();
    $inFile =~ /data_(\d+)_(\d+)/;
    $fileStartID = $1;
    $fileEndID = $2;
    $localcount = 0;
    print "Processing file " . $inFile . "\t";
    my $t= new XML::Twig( TwigHandlers=> { BIOG => \&BIOG },
                          );
    $t->parsefile( $inFile );
    $t->dispose(); # Try to Free memory but does not work...
        
    if ( @localmissing ) {
        push(@missing,@localmissing);
        my $missing = @localmissing;
        print "Missing $missing/$localcount \n";
    } else {
        print "Verified 100%\n";
        my $folder = dirname($inFile);
        $folder =~ s/data_done/data_verified/;
        move($inFile, $folder.basename($inFile));
    }
}


#
# BIOG is XML element we are triggering
#
sub BIOG {
    my ($t, $BIOG)= @_;
    ++$localcount;
    if ( ! checkBiog($BIOG->field('BIOG_NBR')) ) {
        push(@localmissing, $BIOG->field('BIOG_NBR'));
    }    
    $t->purge();  # Tell XML::Twig to dispo of the rest of the tree we
+ don't care about
    return 1;
}

#
# Check database for ID
#
sub checkBiog {
    my ($biog) = @_;
    if ( !%BIOG ) {
        my %where = (
            BIOG_NBR => { -between => [ $fileStartID, $fileEndID ] },
        );
        my($stmt, @bind) = $sql->select('BIOG', '"BIOG_NBR"', \%where)
+;
        if (!$sth) {
            $sth = $dbh->prepare($stmt);
        }
        my $result = $sth->execute(@bind);
        while(my $data = $sth->fetchrow_hashref()) {
            $BIOG{$data->{BIOG_NBR}} = 1;
        }
    }
    if(defined($BIOG{$biog})) {
        return 1;
    } else {
        return 0;
    }
}
[download]