result.language = languages.__all__[lang] # Read NPSL result.input.update( npsl.parseString( "".join(result.input_file.readlines()) )[0] ) result.input.update( get_default_settings( result.input["settings"] ) ) try: result.language.set_options(result, optargs) except RuntimeError, err: raise ArgumentError(err.message) # Make output folder if it doesn't exist if not os.path.exists( result.output_folder ): os.mkdir( result.output_folder ) return result if __name__ == "__main__": optionparser = makeOptionParser() if len( sys.argv ) <= 1: optionparser.print_help() sys.exit(-1) try: o = Output( process_options( optionparser.parse_args() ) ) o.run() except ArgumentError, err: sys.stderr.write( str( err ) + "\r\n" ) sys.exit(-1)
class Collector(DatagramServer):
x = 0
def __init__(self,args):
# create logger
self.logger = logging.getLogger(__name__)
self.logger.setLevel(logging.DEBUG)
# create console handler and set level to debug
ch = logging.StreamHandler()
ch.setLevel(logging.DEBUG)
# create formatter
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
# add formatter to ch
ch.setFormatter(formatter)
# add ch to logger
self.logger.addHandler(ch)
self.logger.debug( "Starting Collector process in %s"%os.getcwd())
#self.logger.debug( "Gevent Version %s"%gevent.__version__)
#TODO: move output file name to config
fname = "./NetFlow.%d.bin"%int(time.time())
#WARN: might want to remove this after testing
self.out = open(fname,"wb")
#create tool instances
self.interface = Interface()
self.parse = Parse()
self.context = Context()
self.describe = Describe()
self.standardize = Standardize()
self.transform = Transform()
self.partition = Partition()
self.q = Queue()
self.inWindow = settings.SETTINGS.get("collector","inWindow")
self.score = Score()
#TODO: move csv name to config
#self.csv = CSV("output.csv")
self.output = Output()
return super(Collector,self).__init__(args)
def done(self):
#pass
self.out.close()
#really important to call del on the csv obj to ensure it closes correctly
#del self.csv
def handle(self, rawData, address):
Collector.x += 1
#print '%s %s: got %r' % (Collector.x, address[0], rawData)
self.out.write(rawData)
interfacedData = self.interface.run(rawData)
#self.logger.debug("Interface: %s"%(repr(interfacedData)))
#once the rawData is "interfaced" we are passing it around by reference
# interfaced data must be iterable
try:
for record in interfacedData:
self.parse.run(record)
#self.logger.debug("Parse: %s"%(repr(record)))
self.context.run(record)
#self.logger.debug("Context: %s"%(repr(record)))
self.describe.run(record)
#self.logger.debug("Describe: %s"%(repr(record)))
#push the record onto the queue until window
if not (self.inWindow):
self.q.put(record)
#self.logger.debug("adding record to queue %s"%(repr(record)))
if (self.q.qsize() == int(settings.SETTINGS.get("collector","describeWindow"))):
#self.logger.debug("Describe Window of %s records met, Begin Processing queue"%settings.SETTINGS.get("collector","describeWindow"))
self.inWindow = True
while not self.q.empty():
item = self.q.get()
#self.logger.debug("processing record from queue %s"%(repr(item)))
self.standardize.run(item)
self.transform.run(item)
self.partition.run(item)
#self.csv.writeRow(self.csv.format(item))
self.output.run(item)
self.q.task_done()
else:
self.standardize.run(record)
#self.logger.debug("Standardize: %s"%(repr(record)))
self.transform.run(record)
#self.logger.debug("Transform: %s"%(repr(record)))
self.partition.run(record)
#self.logger.debug("Partition: %s"%(repr(record)))
#self.csv.writeRow(self.csv.format(record))
self.output.run(record)
#self.score.run(record)
except Exception as e:
self.logger.error("Interfaced data is not iterable %s"%(str(e)))
