khan5v

use strict;
use warnings;

my $spawn_processes = 5;
my $forked = 0;
my $err = 0;
print "($$) parent has started\n";

foreach(1..$spawn_processes) {
    my $child_pid = fork();

khan5v

use strict;
use warnings;

my $child_pid = fork();
if(defined $child_pid && $child_pid > 0) {
    ## Parent
    wait();
    print "p($$) c($child_pid) child finished, exiting\n";
} else {
    ## Child

khan5v

#reading data from a file
logData = sc.textFile(logFile)

X = 10

#for each key finding entries that occur more than X times
outliers = logData.map(lambda (k, v): (k, 1)).reduceByKey(lambda a, b: a + b).filter(lambda (k, v): v > X).cache()

#filtering these entries out

khan5v

# getting an objectId object from a string
getObjectID = function(str) {
    return(mongo.oid.from.string(str))
}

database = ""
mongo = NULL
namespace = ""

connectToMongoDB = function(host, db, collection) {