sabirbagwan commited on
Commit
08b0576
·
1 Parent(s): e08d181

Update preprocess.py

Browse files
Files changed (1) hide show
  1. preprocess.py +6 -0
preprocess.py CHANGED
@@ -8,6 +8,7 @@ def preprocess(data):
8
  pattern1 = r'\d{2}/\d{2}/\d{2}, \d{1,2}:\d{2}[ap]m -'
9
  pattern2 = r'\[\d{2}/\d{2}/\d{2}, \d{2}:\d{2}:\d{2}\]'
10
  pattern3 = r'\d{2}/\d{2}/\d{2}, \d{1,2}:\d{2} -'
 
11
 
12
  # data = "30/06/21, 1:46pm - Gauri Mami turned off disappearing messages."
13
 
@@ -32,6 +33,11 @@ def preprocess(data):
32
  dates = re.findall(pattern3, data)
33
 
34
 
 
 
 
 
 
35
  if not result:
36
  result = None
37
 
 
8
  pattern1 = r'\d{2}/\d{2}/\d{2}, \d{1,2}:\d{2}[ap]m -'
9
  pattern2 = r'\[\d{2}/\d{2}/\d{2}, \d{2}:\d{2}:\d{2}\]'
10
  pattern3 = r'\d{2}/\d{2}/\d{2}, \d{1,2}:\d{2} -'
11
+ pattern4 = r'\d{1,2}/\d{1,2}/\d{2}, \d{2}:\d{2} -'
12
 
13
  # data = "30/06/21, 1:46pm - Gauri Mami turned off disappearing messages."
14
 
 
33
  dates = re.findall(pattern3, data)
34
 
35
 
36
+ if re.search(pattern4, data):
37
+ result.append(data)
38
+ messages = re.split(pattern4, data)[1:]
39
+ dates = re.findall(pattern4, data)
40
+
41
  if not result:
42
  result = None
43