Mercurial > stress-tester
changeset 1269:d7209c062524
flow - do not lowercase paths
| author | Devel 1 |
|---|---|
| date | Fri, 03 Jul 2020 10:24:23 +0200 |
| parents | f3ef02718781 |
| children | 15c0fcd63815 |
| files | stress-tester/src/main/resources/flow_analyzer.py |
| diffstat | 1 files changed, 9 insertions(+), 4 deletions(-) [+] |
line wrap: on
line diff
--- a/stress-tester/src/main/resources/flow_analyzer.py Thu Jul 02 16:49:17 2020 +0200 +++ b/stress-tester/src/main/resources/flow_analyzer.py Fri Jul 03 10:24:23 2020 +0200 @@ -154,7 +154,7 @@ df["datetime"] = pd.to_datetime(df.datetime) self.data = df - def prep_data(self, cleanRows = True, cleanRules = None, dropMissing = True, debug=False): + def prep_data(self, cleanRows = True, cleanRules = None, dropMissing = True, lowercasePath=False, debug=False): if cleanRules is None: self.cleanRules = [ ".css", ".js", @@ -181,8 +181,12 @@ # Proste czyszczenie i normalizowanie stringów (url, request method) - self.data["pathArgs"] = self.data["pathArgs"].str.lower().str.strip() - self.data["pathBase"] = self.data["pathBase"].str.lower().str.strip() + if lowercasePath: + self.data["pathArgs"] = self.data["pathArgs"].str.lower().str.strip() + self.data["pathBase"] = self.data["pathBase"].str.lower().str.strip() + else: + self.data["pathArgs"] = self.data["pathArgs"].str.strip() + self.data["pathBase"] = self.data["pathBase"].str.strip() self.data["requestMethod"] = self.data["requestMethod"].str.lower().str.strip() if dropMissing: @@ -682,6 +686,7 @@ parser.add_argument('-lmax', type=int, default=7) parser.add_argument('-maxSeq', type=int, default=100) parser.add_argument('--fold', action='store_true') + parser.add_argument('--lcase', action='store_true') args = parser.parse_args() cleanRules = [ @@ -701,7 +706,7 @@ analyzer = FlowAnalyzer() analyzer.get_files_list(pathString=args.input) analyzer.get_events_line_csv(dateFormat='%Y-%m-%d_%H_%M_%S_%f') #yyyy-MM-dd_HH_mm_ss_SSS000 - analyzer.prep_data(cleanRules=cleanRules) + analyzer.prep_data(cleanRules=cleanRules, lowercasePath=args.lcase) analyzer.prep_sequences(dropDuplicates=True) for length in range(args.lmin, args.lmax + 1):