def map_count(channel, count_name, temp_dir):
total = LogCounter(count_name)
count = 0
job_id = channel.receive()
while job_id != None:
temp_file_name = "%s/map_%d_%d" % (temp_dir, job_id, count_names.index(count_name))
total.add_counter(pickle.load(open(temp_file_name, 'rb')))
count += 1
os.remove(temp_file_name)
job_id = channel.receive()
channel.send(pickle_to_file(total.report(), "%s/out_%d" % (temp_dir, count_names.index(count_name))))
def parse_chunk(file_name, temp_dir, start, end, job_id):
start_time = time.time()
f = seek_open(file_name, start, end)
mapper = LogMapper()
for line in f:
mapper.parse_line(line)
file_dict = {}
for (count_name, counter) in mapper.get_counters().iteritems():
pickle.dump(counter, open("%s/map_%d_%d" % (temp_dir, job_id, count_names.index(count_name)), 'wb'))
return job_id
