def test_status_count_up(self):
f = open('/Users/len/log-analyer-assignment/tests/fixtures/text.txt',
'r',
encoding="utf-8")
f2 = open(
'/Users/len/log-analyer-assignment/tests/fixtures/output.txt',
'w',
encoding="utf-8")
lines = f.readlines()
file_lists = []
for row in lines:
row_list = custom_log_parser(row)
# data
input_date = datetime.datetime.strptime(
row_list[constants.INDEX_OF_DATETIME_IN_LOG()],
'%d/%b/%Y:%H:%M:%S %z')
row_list[4] = input_date
file_lists.append(row_list)
result = {}
for single_data in file_lists:
http_status = single_data[constants.INDEX_OF_STATUS_NUMBER()]
if http_status in result:
result[http_status] = result[http_status] + 1
else:
result[http_status] = 1
for single_data in result:
print("STATUS CODE {}: COUNT {}".format(single_data,
result[single_data]))
self.assertEqual([], [])
def print_datetime(self, original_dates: list, start_time: str,
end_time: str) -> List:
sorted_list = self.datetime_sort(original_dates)
result_datetime = []
for single_list in sorted_list:
data_date_time = single_list[constants.INDEX_OF_DATETIME_IN_LOG()]
if start_time <= data_date_time <= end_time:
result_datetime.append(single_list)
return result_datetime
def datetime_sort(self, original_dates: list) -> List:
file_lists = []
for row in original_dates:
row_list = LogParserHelper.raw_log_parser(row)
row_list = self.cv_line_str_to_datetime(row_list)
file_lists.append(row_list)
file_lists.sort(key=lambda single_list: single_list[
constants.INDEX_OF_DATETIME_IN_LOG()])
return file_lists
def run(self):
lines = csv.reader(open(file=self.file_path,
newline='',
encoding='utf-8'),
delimiter='|')
function_02 = Function02Impl()
result = {}
for line in tqdm(lines):
rest_api = line[constants.INDEX_OF_REST_API()]
input_date = datetime.datetime.strptime(
line[constants.INDEX_OF_DATETIME_IN_LOG()],
'%d/%b/%Y:%H:%M:%S %z')
if self.start_time <= input_date <= self.end_time:
if function_02.is_satisfied_http_method(line, self.method) is True and \
function_02.is_satisfied_http_status(line, self.code) is True and \
function_02.remove_if_not_static_resource(line):
result = function_02.collect_all_satisfied_request_api(
line)
self._result = result
def run(self):
entries_datetime_zone = []
for i in range(1, len(self.times)):
start_datetime = TimeControlHelper.cv_str_to_datetime(
self.times[i - 1])
end_datetime = TimeControlHelper.cv_str_to_datetime(self.times[i])
datetime_zone = [start_datetime, end_datetime]
entries_datetime_zone.append(datetime_zone)
with open(file=self.file_path, newline='', encoding='utf8') as lines:
lines = csv.reader(lines, delimiter='|')
# 시간대별로 Request 정보에서 Client-Agent 정보를 추출하여 어떤 브라우저(디바이스)에서 접속 했는지 추출함
total_result = {}
for line in tqdm(lines):
if len(line) == 14:
user_time = line[constants.INDEX_OF_DATETIME_IN_LOG()]
input_date = datetime.datetime.strptime(
user_time, '%d/%b/%Y:%H:%M:%S %z')
for start_time_zone, end_time_zone in entries_datetime_zone:
if start_time_zone <= input_date <= end_time_zone:
user_agent = UserAgentHelper.detect_user_agent(
line[constants.INDEX_OF_USER_AGENT()])
if start_time_zone in total_result.keys():
dict_user_agents = total_result[
start_time_zone]
if user_agent in dict_user_agents.keys():
dict_user_agents[
user_agent] = dict_user_agents[
user_agent] + 1
else:
dict_user_agents[user_agent] = 1
total_result[start_time_zone].update(
dict_user_agents)
else:
total_result[start_time_zone] = {}
self._result = total_result
def count_http_status_code(self, files_path: List,
range_times_list: List) -> Dict:
entries_datetime_zone = []
for i in range(1, len(range_times_list)):
start_datetime = TimeControlHelper.cv_str_to_datetime(
range_times_list[i - 1])
end_datetime = TimeControlHelper.cv_str_to_datetime(
range_times_list[i])
datetime_zone = [start_datetime, end_datetime]
entries_datetime_zone.append(datetime_zone)
total_result = {}
for file_path in files_path:
with open(file_path, 'r', encoding='utf8') as lines:
for line in lines:
cv_line = LogParserHelper.csv_log_parser(line)
if len(cv_line) == 14:
http_status = cv_line[
constants.INDEX_OF_STATUS_NUMBER()]
dt_date = cv_line[constants.INDEX_OF_DATETIME_IN_LOG()]
dt_date = TimeControlHelper.cv_str_to_datetime(dt_date)
for start_datetime, end_datetime in entries_datetime_zone:
if start_datetime <= dt_date < end_datetime:
if start_datetime in total_result.keys():
status_dates = total_result[start_datetime]
# {status : key, count : value}
if http_status in status_dates.keys():
status_dates[
http_status] = status_dates[
http_status] + 1
else:
status_dates[http_status] = 1
total_result[start_datetime].update(
status_dates)
else:
total_result[start_datetime] = {}
return total_result
def run(self):
lines = csv.reader(open(file=self.file_path,
newline='',
encoding='utf-8'),
delimiter='|')
MIN = 0.0
for line in tqdm(lines):
input_date = datetime.datetime.strptime(
line[constants.INDEX_OF_DATETIME_IN_LOG()],
'%d/%b/%Y:%H:%M:%S %z')
if self.start_time <= input_date <= self.end_time:
response_time = line[constants.INDEX_OF_RESPONSE_TIME()]
if response_time is not '-':
response_time = float(response_time)
if self.late_time_by_user is not None:
if response_time > MIN:
self._result.append([response_time, line])
elif response_time > MIN:
MIN = response_time
result_log_line = line
self._result = [MIN, result_log_line]
def run(self):
lines = csv.reader(open(file=self.file_path,
newline='',
encoding='utf-8'),
delimiter='|')
function_04 = Function04Impl()
result = {}
for line in tqdm(lines):
input_date = datetime.datetime.strptime(
line[constants.INDEX_OF_DATETIME_IN_LOG()],
'%d/%b/%Y:%H:%M:%S %z')
if self.start_time <= input_date <= self.end_time:
if function_04.remove_if_not_static_resource(
line[constants.INDEX_OF_REST_API()]):
continue
else:
rest_api = line[constants.INDEX_OF_REST_API()]
if rest_api in result:
result[rest_api] = result[rest_api] + 1
else:
result[rest_api] = 1
self._result = result
def cv_line_str_to_datetime(row_list) -> datetime:
input_date = datetime.datetime.strptime(
row_list[constants.INDEX_OF_DATETIME_IN_LOG()],
'%d/%b/%Y:%H:%M:%S %z')
row_list[constants.INDEX_OF_DATETIME_IN_LOG()] = input_date
return row_list