From 9fedd3913dc2c797a4b7dd8261a47424b5d02fce Mon Sep 17 00:00:00 2001
From: sasi <sasi>
Date: Wed, 8 Dec 2021 11:50:35 +0530
Subject: [PATCH 1/8] Date and time issue in whatsapp chat

---
 .DS_Store                  | Bin 0 -> 6148 bytes
 src/chat_analyzer.py       | 116 +++++++++++++++++++++++++++++++------
 tests/.DS_Store            | Bin 0 -> 6148 bytes
 tests/test_chats/.DS_Store | Bin 0 -> 6148 bytes
 4 files changed, 99 insertions(+), 17 deletions(-)
 create mode 100644 .DS_Store
 create mode 100644 tests/.DS_Store
 create mode 100644 tests/test_chats/.DS_Store

diff --git a/.DS_Store b/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..ac713db6418ccd8f1becaaf4e906fdb173607add
GIT binary patch
literal 6148
zcmeHKO-lnY5PfMYws`4Hk9*XEE}p%t{WyqUpomxP2Uu*ob-RV?X@7=)!QbZ(&^Jja
z-L0Yr5s?{4UNV`P%)G#61Hd$9y?vk#pvop#s<Hb(WL?^dl)Pr0Xe7qbFz$ASaffpW
zsPgw2kh80xhZtQ<3+MO3we2@6wvZYw(8eKJI3@03gkIjmY!*D~NYKXvW*FGfh_f+L
zOzE9sj&zcCPG-|Iq2CU!sPEHmijW!IGX8{~34KHE*{A-VUNN;Hj&Y51G&ySGj<zXw
znc0}5As+E$<AjX*oea)=24C7TUYS`W=oadJE!4fnd?a61nzzIOEuWV-UAGm@$;W`%
z4+_?D0?XE%swe}>fHLp{4DiktsctybUKvmZlz{~U@_h){1S5}`L;LAqXP*GX3e{FP
zw!i+wKorEtW9E<=igB()=W6^D!}ynjaqe7?ynW`-xx?6<8OQHz{0qhShldHQIZWhG
zdu2cw$TLuO)4JUM?a$x;c_*DI1Ioa^V!%{dm#qd%@^|Y>adOuNY&UEoVwX8wxNu;v
gV%o}8yv1gP`alN6$YbV^8jAi1SQ@lb27Z-+cY^$Mp8x;=

literal 0
HcmV?d00001

diff --git a/src/chat_analyzer.py b/src/chat_analyzer.py
index 662a0f8..e5a22df 100644
--- a/src/chat_analyzer.py
+++ b/src/chat_analyzer.py
@@ -20,12 +20,28 @@
 """
 # For Whatsapp chat exports
 WUser = r'(- (?P<username>[^:]*):)'  # To get the user's name
-# To get the date
-WDate = r'(?P<date>(?P<month>[0-9]{1,2})[-\/]{1}(?P<day>[0-9]{1,2})[-\/]{1}(?P<year>[0-9]{2}))'
-# To get the time
-WTime = r'(, (?P<time>(?P<hour>[0-9]{2}):(?P<minute>[0-9]{2})) )'
+
+# To get the date if it is in the format m/d/y(type1)
+WDatetype1 = r'(?P<datetype1>(?P<monthtype1>[0-9]{1,2})[-\/]{1}(?P<daytype1>[0-9]{1,2})[-\/]{1}(?P<yeartype1>[0-9]{2,4}))'
+# To get the date if it is in the format d/m/y(type2)
+WDatetype2 = r'(?P<datetype2>(?P<daytype2>[0-9]{1,2})[-\/]{1}(?P<monthtype2>[0-9]{1,2})[-\/]{1}(?P<yeartype2>[0-9]{2,4}))'
+# To get the date if it is in the format y/m/d(type3)
+WDatetype3 = r'(?P<datetype3>(?P<yeartype3>[0-9]{2,4})[-\/]{1}(?P<monthtype3>[0-9]{1,2})[-\/]{1}(?P<daytype3>[0-9]{1,2}))'
+
+# To get the time in 12hr clock
+WTimeHour12 = r'(, (?P<time>(?P<hour>[0-9]{1,2}):(?P<minute>[0-9]{2}) (?P<ampm>[AP]M)) )'
+# To get the time in 24hr clock
+WTimeHour24 = r'(, (?P<time>(?P<hour>[0-9]{1,2}):(?P<minute>[0-9]{2})) )'
+
 # Finally to get the parsed message
-WMsg = WDate + WTime + WUser + r'(?P<message>.*)'
+WMsgtype1Hour12 = WDatetype1 + WTimeHour12 + WUser + r'(?P<message>.*)'
+WMsgtype1Hour24 = WDatetype1 + WTimeHour24 + WUser + r'(?P<message>.*)'
+
+WMsgtype2Hour12 = WDatetype2 + WTimeHour12 + WUser + r'(?P<message>.*)'
+WMsgtype2Hour24 = WDatetype2 + WTimeHour24 + WUser + r'(?P<message>.*)'
+
+WMsgtype3Hour12 = WDatetype3 + WTimeHour12 + WUser + r'(?P<message>.*)'
+WMsgtype3Hour24 = WDatetype3 + WTimeHour24 + WUser + r'(?P<message>.*)'
 
 # For Signal chat exports
 SDate = r'(?P<date>(?P<year>[0-9]{4})-(?P<month>[0-9]{2})-(?P<day>[0-9]{2}))'
@@ -150,8 +166,13 @@ def import_data(path_to_chatfile: str) -> List[Dict[str, Any]]:
     for line_num, line in enumerate(f):
         if line_num > globals.WHATSAPP_MEMBER_LIMIT:
             break
-        match = re.search(WMsg, line)
-        if match:
+        match1Hour12 = re.search(WMsgtype1Hour12, line)
+        match1Hour24 = re.search(WMsgtype1Hour24, line)
+        match2Hour12 = re.search(WMsgtype2Hour12, line)
+        match2Hour24 = re.search(WMsgtype2Hour24, line)
+        match3Hour12 = re.search(WMsgtype3Hour12, line)
+        match3Hour24 = re.search(WMsgtype3Hour24, line)
+        if match1Hour12 or match1Hour24 or match2Hour12 or match2Hour24 or match3Hour12 or match3Hour24 :
             isWa = True
             break
 
@@ -159,20 +180,81 @@ def import_data(path_to_chatfile: str) -> List[Dict[str, Any]]:
         print('Whatsapp chat recognized')
         f.seek(0)
         for line in f:
-            match = re.search(WMsg, line)
-            if match:
+            match1Hour12 = re.search(WMsgtype1Hour12, line)
+            match1Hour24 = re.search(WMsgtype1Hour24, line)
+            match2Hour12 = re.search(WMsgtype2Hour12, line)
+            match2Hour24 = re.search(WMsgtype2Hour24, line)
+            match3Hour12 = re.search(WMsgtype3Hour12, line)
+            match3Hour24 = re.search(WMsgtype3Hour24, line)
+            if match1Hour12 and 1<=int(match1Hour12.groupdict()['daytype1'])<=31 and 1<=int(match1Hour12.groupdict()['monthtype1'])<=12 :
                 msgs.append({
-                    'username': match.groupdict()['username'],
-                    'date': datetime.strptime(match.groupdict()['date'], '%m/%d/%y').date(),
-                    'month': match.groupdict()['month'],
-                    'day': match.groupdict()['day'],
-                    'year': match.groupdict()['year'],
-                    'time': datetime.strptime(match.groupdict()['time'], '%H:%M').time(),
-                    'hour': match.groupdict()['hour'],
-                    'minute': match.groupdict()['minute'],
+                    'username': match1Hour12.groupdict()['username'],
+                    'date': datetime.strptime(match1Hour12.groupdict()['datetype1'], '%m/%d/%y').date(),
+                    'month': match1Hour12.groupdict()['monthtype1'],
+                    'day': match1Hour12.groupdict()['daytype1'],
+                    'year': match1Hour12.groupdict()['yeartype1'],
+                    'time': datetime.strptime(match1Hour12.groupdict()['time'], '%I:%M %p').time(),
+                    'hour': match1Hour12.groupdict()['hour'],
+                    'minute': match1Hour12.groupdict()['minute'],
+                })
+            elif match1Hour24 and 1<=int(match1Hour24.groupdict()['daytype1'])<=31 and 1<=int(match1Hour24.groupdict()['monthtype1'])<=12 :
+                msgs.append({
+                    'username': match1Hour24.groupdict()['username'],
+                    'date': datetime.strptime(match1Hour24.groupdict()['datetype1'], '%m/%d/%y').date(),
+                    'month': match1Hour24.groupdict()['monthtype1'],
+                    'day': match1Hour24.groupdict()['daytype1'],
+                    'year': match1Hour24.groupdict()['yeartype1'],
+                    'time': datetime.strptime(match1Hour24.groupdict()['time'], '%H:%M').time(),
+                    'hour': match1Hour24.groupdict()['hour'],
+                    'minute': match1Hour24.groupdict()['minute'],
+                })
+            elif match2Hour12 and 1<=int(match2Hour12.groupdict()['daytype2'])<=31 and 1<=int(match2Hour12.groupdict()['monthtype2'])<=12 :
+                msgs.append({
+                    'username': match2Hour12.groupdict()['username'],
+                    'date': datetime.strptime(match2Hour12.groupdict()['datetype2'], '%d/%m/%y').date(),
+                    'month': match2Hour12.groupdict()['monthtype2'],
+                    'day': match2Hour12.groupdict()['daytype2'],
+                    'year': match2Hour12.groupdict()['yeartype2'],
+                    'time': datetime.strptime(match2Hour12.groupdict()['time'], '%I:%M %p').time(),
+                    'hour': match2Hour12.groupdict()['hour'],
+                    'minute': match2Hour12.groupdict()['minute'],
+                })
+            elif match2Hour24 and 1<=int(match2Hour24.groupdict()['daytype2'])<=31 and 1<=int(match2Hour24.groupdict()['monthtype2'])<=12 :
+                msgs.append({
+                    'username': match2Hour24.groupdict()['username'],
+                    'date': datetime.strptime(match2Hour24.groupdict()['datetype2'], '%d/%m/%y').date(),
+                    'month': match2Hour24.groupdict()['monthtype2'],
+                    'day': match2Hour24.groupdict()['daytype2'],
+                    'year': match2Hour24.groupdict()['yeartype2'],
+                    'time': datetime.strptime(match2Hour24.groupdict()['time'], '%H:%M').time(),
+                    'hour': match2Hour24.groupdict()['hour'],
+                    'minute': match2Hour24.groupdict()['minute'],
+                })
+            elif match3Hour12 and 1<=int(match3Hour12.groupdict()['daytype3'])<=31 and 1<=int(match3Hour12.groupdict()['monthtype3'])<=12 :
+                msgs.append({
+                    'username': match3Hour12.groupdict()['username'],
+                    'date': datetime.strptime(match3Hour12.groupdict()['datetype3'], '%d/%m/%y').date(),
+                    'month': match3Hour12.groupdict()['monthtype3'],
+                    'day': match3Hour12.groupdict()['daytype3'],
+                    'year': match3Hour12.groupdict()['yeartype3'],
+                    'time': datetime.strptime(match3Hour12.groupdict()['time'], '%I:%M %p').time(),
+                    'hour': match3Hour12.groupdict()['hour'],
+                    'minute': match3Hour12.groupdict()['minute'],
+                })
+            elif match3Hour24 and 1<=int(match3Hour24.groupdict()['daytype3'])<=31 and 1<=int(match3Hour24.groupdict()['monthtype3'])<=12 :
+                msgs.append({
+                    'username': match3Hour24.groupdict()['username'],
+                    'date': datetime.strptime(match3Hour24.groupdict()['datetype3'], '%y/%m/%d').date(),
+                    'month': match3Hour24.groupdict()['monthtype3'],
+                    'day': match3Hour24.groupdict()['daytype3'],
+                    'year': match3Hour24.groupdict()['yeartype3'],
+                    'time': datetime.strptime(match3Hour24.groupdict()['time'], '%H:%M').time(),
+                    'hour': match3Hour24.groupdict()['hour'],
+                    'minute': match3Hour24.groupdict()['minute'],
                 })
         f.close()
         return msgs
+
     f.close()
 
     print('Invalid file!')
diff --git a/tests/.DS_Store b/tests/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..f2f1ae24ed0a5cf2f4793f3502b4c51921f97b0a
GIT binary patch
literal 6148
zcmeHKPfNov6i>FP*+kqyn8#ea?XanAco0gR2X8_}4=P*hhAYf=ter*cq#r}Sk>9|t
z<9kUq9GfRWWV{D2znAwXA-|NQVT^Hm+^sWKW{e3?#9R@YC4zC(1<4r?B3EOy*&XXM
zm&Ghv$R@{sWB~WB1pC#49gEqw{qvG&=nX;-;ve2{;74(-_Q`Yk!rJ<V5G7ICD&0E$
zFmYlx9!Iu2y2jqQ8}~h9UxeXcX1m^{-%Hx%os%$#T|elJRI%UfLCVdQA9TaS4#z<^
zQsX!}AVg6V+vQ4{){m-kzi~9F%Cy<6RpsG9V=^g<%3l5Wtn={noW4w6-!#D-zC|V5
z2B+{2#?rMuI-_6^2KNx3)=p~(i2-7O7+6IH%vmQkS8;K)CSrgX_!R?qK1fhR%V4Ha
z9Uai%?<2+wh$vv=TLMuUv<zk%Ap*j6DWERp=83^|Iryc?vkYb$bvff|W*EoJ%*_jh
ztJ%RXRXXFAMrw%xVql(uyzZ9q{y+Ws{XbtsJz{_uSSbd0q2;t}SdzJ07Z!(itpx3W
qqF`R8aaIC`x{4teui{-$CE%B609pn!jo<;H9|1)JHN?Q5GVle+B2(l5

literal 0
HcmV?d00001

diff --git a/tests/test_chats/.DS_Store b/tests/test_chats/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..7822c604a135a8a71f9b17b3006bf9280f74ad0a
GIT binary patch
literal 6148
zcmeHKJx{|h5PdEM6|r<=%paf;D^qC01cCt}#_|yah_9+~#K)AM&O7^BB`vH_!JTw|
z_WADYyjXD#fE!lDF3<<iqY8F5*?b`~FS;ZhwRDLt<R~Wo>ZmIHbjjBYtI2@8yLFVf
z#Q;xezP~-3(SCy|+Y|*ZIX^+g@jb^mXG%Q4<Av4~hd9RxM(mAnM_-Q}?BkieN4(=B
z<Vk6jC?7J;`eR&cgsii;n`1pqjXlz51Fy_HV5T?t#+m!AJumKOw(FLCH4lL8$`~*P
z{v`vvvqgGa5v?@_i~(a{&VYO$5~^UPSVs(>4mP0#Aj)rK5cZ{(keEa<Q>-I$hT>u<
zF@`!VF<cC%JyE|*v5pwS;k5X0y0X&>#f8<GKMC$|Sww4%0b`)ez*-#k<^DhTzW#3q
z*~l0$2L2QSuA86cLq3w;txFFlcWpwwpo)lJ9dRDQPPmHcD_8M0H3;pAbcmT^9g!A_
O{RjjatT6_Dlz~sA#8g`V

literal 0
HcmV?d00001


From 23898350c3bd38e3ea47bab8b0c2c1aed75b23ad Mon Sep 17 00:00:00 2001
From: sasi <sasi>
Date: Sat, 11 Dec 2021 14:14:27 +0530
Subject: [PATCH 2/8] date-issue whatsapp

---
 .DS_Store            | Bin 6148 -> 6148 bytes
 src/chat_analyzer.py | 154 ++++++++++++++++---------------------------
 2 files changed, 58 insertions(+), 96 deletions(-)

diff --git a/.DS_Store b/.DS_Store
index ac713db6418ccd8f1becaaf4e906fdb173607add..4a7571a4aaac85a71667e56e03a1d85f34b251db 100644
GIT binary patch
delta 437
zcmZoMXfc=|#>B!ku~2NHo+2af#(>?7i!U%UG4f94VbYFZVMt-fXGmr!&dqmmNy^Dj
zVqjq4XcAa+qj&vbM<5$XJ_WCQL55*)a(-?BP!A9YOg3f;7x2u<PllQ)02H*|9K~eF
zSkKB(!jQ^P3?z$_%8Lu23Qi^!<YX3?7#Lh<WMXDvWn<^y;Nsxo<%$i?$S)5rNh~QX
zc1kRY2Jr$COEQw6?2!EY95_2MDJ(O!JYGP=IX|x?F*7f<2&_3XB^9V7COk7QCBNLM
zKEE_Cr5J2bFhqufgOh_ZUO=L{+SJ%gN5R;_yjDk{+T7egN5RC{thSbuLtNF+)-xfu
zvZ}hKwr(cahYXC25SoD>O2epGKn9W@%YuvYa`N-ifubNC?2~(#A8lsm;O78F%I1U2
W-<c=#i#T!srI<hlY>p6F!wdkJ1aa^H

delta 76
zcmZoMXfc=|#>B)qu~2NHo+2ar#(>?7jO>$nShOckW(nS`#>&VzS%v-aW(AI!%$wOc
f_&I=THw$unXP(S2;>f`O1dI#}ESn=l)-VGA<^mC-

diff --git a/src/chat_analyzer.py b/src/chat_analyzer.py
index e5a22df..f9c620d 100644
--- a/src/chat_analyzer.py
+++ b/src/chat_analyzer.py
@@ -20,28 +20,12 @@
 """
 # For Whatsapp chat exports
 WUser = r'(- (?P<username>[^:]*):)'  # To get the user's name
-
-# To get the date if it is in the format m/d/y(type1)
-WDatetype1 = r'(?P<datetype1>(?P<monthtype1>[0-9]{1,2})[-\/]{1}(?P<daytype1>[0-9]{1,2})[-\/]{1}(?P<yeartype1>[0-9]{2,4}))'
-# To get the date if it is in the format d/m/y(type2)
-WDatetype2 = r'(?P<datetype2>(?P<daytype2>[0-9]{1,2})[-\/]{1}(?P<monthtype2>[0-9]{1,2})[-\/]{1}(?P<yeartype2>[0-9]{2,4}))'
-# To get the date if it is in the format y/m/d(type3)
-WDatetype3 = r'(?P<datetype3>(?P<yeartype3>[0-9]{2,4})[-\/]{1}(?P<monthtype3>[0-9]{1,2})[-\/]{1}(?P<daytype3>[0-9]{1,2}))'
-
-# To get the time in 12hr clock
-WTimeHour12 = r'(, (?P<time>(?P<hour>[0-9]{1,2}):(?P<minute>[0-9]{2}) (?P<ampm>[AP]M)) )'
-# To get the time in 24hr clock
-WTimeHour24 = r'(, (?P<time>(?P<hour>[0-9]{1,2}):(?P<minute>[0-9]{2})) )'
-
+# To get the date
+WDate = r'(?P<date>(?P<feild1>[0-9]{1,4})[-\/]{1}(?P<feild2>[0-9]{1,2})[-\/]{1}(?P<feild3>[0-9]{1,4}))'
+# To get the time
+WTime = r'(, (?P<time>(?P<hour>[0-9]{1,2}):(?P<minute>[0-9]{2})) )'
 # Finally to get the parsed message
-WMsgtype1Hour12 = WDatetype1 + WTimeHour12 + WUser + r'(?P<message>.*)'
-WMsgtype1Hour24 = WDatetype1 + WTimeHour24 + WUser + r'(?P<message>.*)'
-
-WMsgtype2Hour12 = WDatetype2 + WTimeHour12 + WUser + r'(?P<message>.*)'
-WMsgtype2Hour24 = WDatetype2 + WTimeHour24 + WUser + r'(?P<message>.*)'
-
-WMsgtype3Hour12 = WDatetype3 + WTimeHour12 + WUser + r'(?P<message>.*)'
-WMsgtype3Hour24 = WDatetype3 + WTimeHour24 + WUser + r'(?P<message>.*)'
+WMsg = WDate + WTime + WUser + r'(?P<message>.*)'
 
 # For Signal chat exports
 SDate = r'(?P<date>(?P<year>[0-9]{4})-(?P<month>[0-9]{2})-(?P<day>[0-9]{2}))'
@@ -166,95 +150,73 @@ def import_data(path_to_chatfile: str) -> List[Dict[str, Any]]:
     for line_num, line in enumerate(f):
         if line_num > globals.WHATSAPP_MEMBER_LIMIT:
             break
-        match1Hour12 = re.search(WMsgtype1Hour12, line)
-        match1Hour24 = re.search(WMsgtype1Hour24, line)
-        match2Hour12 = re.search(WMsgtype2Hour12, line)
-        match2Hour24 = re.search(WMsgtype2Hour24, line)
-        match3Hour12 = re.search(WMsgtype3Hour12, line)
-        match3Hour24 = re.search(WMsgtype3Hour24, line)
-        if match1Hour12 or match1Hour24 or match2Hour12 or match2Hour24 or match3Hour12 or match3Hour24 :
+        match = re.search(WMsg, line)
+        if match:
             isWa = True
             break
 
     if isWa:
         print('Whatsapp chat recognized')
         f.seek(0)
+        #To check the dateformats
+        formatdmy = 1
+        formatmdy = 1
+        formatymd = 1
+        #To check that the date formats in the chat are in which format
+        #Can also check the time format here itself...
         for line in f:
-            match1Hour12 = re.search(WMsgtype1Hour12, line)
-            match1Hour24 = re.search(WMsgtype1Hour24, line)
-            match2Hour12 = re.search(WMsgtype2Hour12, line)
-            match2Hour24 = re.search(WMsgtype2Hour24, line)
-            match3Hour12 = re.search(WMsgtype3Hour12, line)
-            match3Hour24 = re.search(WMsgtype3Hour24, line)
-            if match1Hour12 and 1<=int(match1Hour12.groupdict()['daytype1'])<=31 and 1<=int(match1Hour12.groupdict()['monthtype1'])<=12 :
-                msgs.append({
-                    'username': match1Hour12.groupdict()['username'],
-                    'date': datetime.strptime(match1Hour12.groupdict()['datetype1'], '%m/%d/%y').date(),
-                    'month': match1Hour12.groupdict()['monthtype1'],
-                    'day': match1Hour12.groupdict()['daytype1'],
-                    'year': match1Hour12.groupdict()['yeartype1'],
-                    'time': datetime.strptime(match1Hour12.groupdict()['time'], '%I:%M %p').time(),
-                    'hour': match1Hour12.groupdict()['hour'],
-                    'minute': match1Hour12.groupdict()['minute'],
-                })
-            elif match1Hour24 and 1<=int(match1Hour24.groupdict()['daytype1'])<=31 and 1<=int(match1Hour24.groupdict()['monthtype1'])<=12 :
-                msgs.append({
-                    'username': match1Hour24.groupdict()['username'],
-                    'date': datetime.strptime(match1Hour24.groupdict()['datetype1'], '%m/%d/%y').date(),
-                    'month': match1Hour24.groupdict()['monthtype1'],
-                    'day': match1Hour24.groupdict()['daytype1'],
-                    'year': match1Hour24.groupdict()['yeartype1'],
-                    'time': datetime.strptime(match1Hour24.groupdict()['time'], '%H:%M').time(),
-                    'hour': match1Hour24.groupdict()['hour'],
-                    'minute': match1Hour24.groupdict()['minute'],
-                })
-            elif match2Hour12 and 1<=int(match2Hour12.groupdict()['daytype2'])<=31 and 1<=int(match2Hour12.groupdict()['monthtype2'])<=12 :
-                msgs.append({
-                    'username': match2Hour12.groupdict()['username'],
-                    'date': datetime.strptime(match2Hour12.groupdict()['datetype2'], '%d/%m/%y').date(),
-                    'month': match2Hour12.groupdict()['monthtype2'],
-                    'day': match2Hour12.groupdict()['daytype2'],
-                    'year': match2Hour12.groupdict()['yeartype2'],
-                    'time': datetime.strptime(match2Hour12.groupdict()['time'], '%I:%M %p').time(),
-                    'hour': match2Hour12.groupdict()['hour'],
-                    'minute': match2Hour12.groupdict()['minute'],
-                })
-            elif match2Hour24 and 1<=int(match2Hour24.groupdict()['daytype2'])<=31 and 1<=int(match2Hour24.groupdict()['monthtype2'])<=12 :
+            match = re.search(WMsg, line)
+            if match:
+                try:
+                    datetime_object = datetime.strptime(match.groupdict()['date'], '%m/%d/%y')
+                except:
+                    formatmdy = 0
+                try:
+                    datetime_object = datetime.strptime(match.groupdict()['date'], '%d/%m/%y')
+                except:
+                    formatdmy = 0
+                try:
+                    datetime_object = datetime.strptime(match.groupdict()['date'], '%y/%m/%d')
+                except:
+                    formatymd = 0    
+        f.seek(0)
+        for line in f:
+            match = re.search(WMsg, line)
+            if match and formatmdy:
                 msgs.append({
-                    'username': match2Hour24.groupdict()['username'],
-                    'date': datetime.strptime(match2Hour24.groupdict()['datetype2'], '%d/%m/%y').date(),
-                    'month': match2Hour24.groupdict()['monthtype2'],
-                    'day': match2Hour24.groupdict()['daytype2'],
-                    'year': match2Hour24.groupdict()['yeartype2'],
-                    'time': datetime.strptime(match2Hour24.groupdict()['time'], '%H:%M').time(),
-                    'hour': match2Hour24.groupdict()['hour'],
-                    'minute': match2Hour24.groupdict()['minute'],
+                    'username': match.groupdict()['username'],
+                    'date': datetime.strptime(match.groupdict()['date'], '%m/%d/%y').date(),
+                    'month': match.groupdict()['feild1'],
+                    'day': match.groupdict()['feild2'],
+                    'year': match.groupdict()['feild3'],
+                    'time': datetime.strptime(match.groupdict()['time'], '%H:%M').time(),
+                    'hour': match.groupdict()['hour'],
+                    'minute': match.groupdict()['minute'],
                 })
-            elif match3Hour12 and 1<=int(match3Hour12.groupdict()['daytype3'])<=31 and 1<=int(match3Hour12.groupdict()['monthtype3'])<=12 :
+            elif match and formatdmy:
                 msgs.append({
-                    'username': match3Hour12.groupdict()['username'],
-                    'date': datetime.strptime(match3Hour12.groupdict()['datetype3'], '%d/%m/%y').date(),
-                    'month': match3Hour12.groupdict()['monthtype3'],
-                    'day': match3Hour12.groupdict()['daytype3'],
-                    'year': match3Hour12.groupdict()['yeartype3'],
-                    'time': datetime.strptime(match3Hour12.groupdict()['time'], '%I:%M %p').time(),
-                    'hour': match3Hour12.groupdict()['hour'],
-                    'minute': match3Hour12.groupdict()['minute'],
+                    'username': match.groupdict()['username'],
+                    'date': datetime.strptime(match.groupdict()['date'], '%d/%m/%y').date(),
+                    'month': match.groupdict()['feild2'],
+                    'day': match.groupdict()['feild1'],
+                    'year': match.groupdict()['feild3'],
+                    'time': datetime.strptime(match.groupdict()['time'], '%H:%M').time(),
+                    'hour': match.groupdict()['hour'],
+                    'minute': match.groupdict()['minute'],
                 })
-            elif match3Hour24 and 1<=int(match3Hour24.groupdict()['daytype3'])<=31 and 1<=int(match3Hour24.groupdict()['monthtype3'])<=12 :
+            elif match and formatymd:
                 msgs.append({
-                    'username': match3Hour24.groupdict()['username'],
-                    'date': datetime.strptime(match3Hour24.groupdict()['datetype3'], '%y/%m/%d').date(),
-                    'month': match3Hour24.groupdict()['monthtype3'],
-                    'day': match3Hour24.groupdict()['daytype3'],
-                    'year': match3Hour24.groupdict()['yeartype3'],
-                    'time': datetime.strptime(match3Hour24.groupdict()['time'], '%H:%M').time(),
-                    'hour': match3Hour24.groupdict()['hour'],
-                    'minute': match3Hour24.groupdict()['minute'],
+                    'username': match.groupdict()['username'],
+                    'date': datetime.strptime(match.groupdict()['date'], '%y/%m/%d').date(),
+                    'month': match.groupdict()['feild2'],
+                    'day': match.groupdict()['feild3'],
+                    'year': match.groupdict()['feild1'],
+                    'time': datetime.strptime(match.groupdict()['time'], '%H:%M').time(),
+                    'hour': match.groupdict()['hour'],
+                    'minute': match.groupdict()['minute'],
                 })
         f.close()
         return msgs
-
     f.close()
 
     print('Invalid file!')
@@ -331,4 +293,4 @@ def controller(
 
 
 if __name__ == '__main__':
-    controller()
+    controller()
\ No newline at end of file

From 4ac858b322aee596cd95cd96a8cefc751b417387 Mon Sep 17 00:00:00 2001
From: sasi <sasi>
Date: Sat, 11 Dec 2021 14:36:00 +0530
Subject: [PATCH 3/8] .DS_Store banished!

---
 .DS_Store                  | Bin 6148 -> 0 bytes
 .gitignore                 |   1 +
 tests/.DS_Store            | Bin 6148 -> 0 bytes
 tests/test_chats/.DS_Store | Bin 6148 -> 0 bytes
 4 files changed, 1 insertion(+)
 delete mode 100644 .DS_Store
 delete mode 100644 tests/.DS_Store
 delete mode 100644 tests/test_chats/.DS_Store

diff --git a/.DS_Store b/.DS_Store
deleted file mode 100644
index 4a7571a4aaac85a71667e56e03a1d85f34b251db..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 6148
zcmeHK&2G~`5T0#P>I7BffYcs+K>{g|RDlKwA*D%rsQ48IdH~egvDH{4-e5bVZ3v3E
za|hl435kc`#1p`K@Br}b4^@%^6$cPSJJRkqyE`*G^EviriHOzv{t8inh%7XL**v-*
zh*%fxkj&|sMIaL~HafiJb-0JI2x!DGU>Nwf84&MomVDyWqGaa%eT%iTU!}+*4(z(T
z+0^g3^`h|Z^UL=i)+Xb0x&O=cUVFu9@orB>RiBC+-Jx|_qbA(|UZ5`d)7h}4nQRIa
zQ$SCsPodPh7)6v)0`HV|DV_GGE5GaCOTFv;B#q&Bj_x6DfPE4wfh`yL^{{h{y-UbB
z!2DzE$}wA_YqUwXr~$1(ZP=!C9+gGVI<!aoGENCmkE{S0+|(HyX^VInWD!$qx^DJm
zrtW#<Bk~1P)0UE<R};^B!qOWgJ^jQ#dc97Vq~-D_HkZlHpIET0yp><fKXTf9;G}Na
zPwH;`K#Xp?Y1`BKUCuiPy6fE!gTYqebc08!8%9AaokKr>$-~Vs^7)|7`;ni>IF4Gd
ztelnGDl89&mny48yK=cYD%!(pwOq6>R#r!&oV9dj<?6<EcW;0AZ1ns!3WqQpO;S#2
z{0?uROqBT4iK7mWb}%bE7UbjH#g8e(qYG!K60gQ2RTv&W(ZpCMk6-F0W5a-9;14q(
zz7IB<z?#OfLiy=HC$9j&ET*MEmw)|%wwM6cG>#Qw2EvppP`NUF#bEm8z?3`IYubLS
zP`MM6J0p(Xndut}(-#kBOLJm1g{C(Q7zU;p$f#jKod4@TzyD7=nUP_@Fz{b7z_LxJ
zSw~6wY&}$*IBRXRZ8RamZmdwcpwq{(RK!udj3xzZworgIjbnwFftWu6k_OWm2L37o
F-vF!6-&6nq

diff --git a/.gitignore b/.gitignore
index 6bdcf72..139b229 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,2 +1,3 @@
 __pycache__/
 .vim/
+.DS_Store
diff --git a/tests/.DS_Store b/tests/.DS_Store
deleted file mode 100644
index f2f1ae24ed0a5cf2f4793f3502b4c51921f97b0a..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 6148
zcmeHKPfNov6i>FP*+kqyn8#ea?XanAco0gR2X8_}4=P*hhAYf=ter*cq#r}Sk>9|t
z<9kUq9GfRWWV{D2znAwXA-|NQVT^Hm+^sWKW{e3?#9R@YC4zC(1<4r?B3EOy*&XXM
zm&Ghv$R@{sWB~WB1pC#49gEqw{qvG&=nX;-;ve2{;74(-_Q`Yk!rJ<V5G7ICD&0E$
zFmYlx9!Iu2y2jqQ8}~h9UxeXcX1m^{-%Hx%os%$#T|elJRI%UfLCVdQA9TaS4#z<^
zQsX!}AVg6V+vQ4{){m-kzi~9F%Cy<6RpsG9V=^g<%3l5Wtn={noW4w6-!#D-zC|V5
z2B+{2#?rMuI-_6^2KNx3)=p~(i2-7O7+6IH%vmQkS8;K)CSrgX_!R?qK1fhR%V4Ha
z9Uai%?<2+wh$vv=TLMuUv<zk%Ap*j6DWERp=83^|Iryc?vkYb$bvff|W*EoJ%*_jh
ztJ%RXRXXFAMrw%xVql(uyzZ9q{y+Ws{XbtsJz{_uSSbd0q2;t}SdzJ07Z!(itpx3W
qqF`R8aaIC`x{4teui{-$CE%B609pn!jo<;H9|1)JHN?Q5GVle+B2(l5

diff --git a/tests/test_chats/.DS_Store b/tests/test_chats/.DS_Store
deleted file mode 100644
index 7822c604a135a8a71f9b17b3006bf9280f74ad0a..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 6148
zcmeHKJx{|h5PdEM6|r<=%paf;D^qC01cCt}#_|yah_9+~#K)AM&O7^BB`vH_!JTw|
z_WADYyjXD#fE!lDF3<<iqY8F5*?b`~FS;ZhwRDLt<R~Wo>ZmIHbjjBYtI2@8yLFVf
z#Q;xezP~-3(SCy|+Y|*ZIX^+g@jb^mXG%Q4<Av4~hd9RxM(mAnM_-Q}?BkieN4(=B
z<Vk6jC?7J;`eR&cgsii;n`1pqjXlz51Fy_HV5T?t#+m!AJumKOw(FLCH4lL8$`~*P
z{v`vvvqgGa5v?@_i~(a{&VYO$5~^UPSVs(>4mP0#Aj)rK5cZ{(keEa<Q>-I$hT>u<
zF@`!VF<cC%JyE|*v5pwS;k5X0y0X&>#f8<GKMC$|Sww4%0b`)ez*-#k<^DhTzW#3q
z*~l0$2L2QSuA86cLq3w;txFFlcWpwwpo)lJ9dRDQPPmHcD_8M0H3;pAbcmT^9g!A_
O{RjjatT6_Dlz~sA#8g`V


From 8fd1dfbcf59c825d686e522914dab8a0b9495863 Mon Sep 17 00:00:00 2001
From: sasi <sasi>
Date: Tue, 14 Dec 2021 17:57:22 +0530
Subject: [PATCH 4/8] .DS_Store banished!

---
 src/.gitignore | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 src/.gitignore

diff --git a/src/.gitignore b/src/.gitignore
new file mode 100644
index 0000000..e43b0f9
--- /dev/null
+++ b/src/.gitignore
@@ -0,0 +1 @@
+.DS_Store

From bff6ca208d78abe1cca3af2503d456918bb891fa Mon Sep 17 00:00:00 2001
From: sasi <sasi>
Date: Tue, 14 Dec 2021 17:59:47 +0530
Subject: [PATCH 5/8] Date issue Revised 1.1

---
 src/chat_analyzer.py    | 72 ++++++++++++++++++-----------------------
 tests/test_chats/wa.txt |  2 +-
 2 files changed, 32 insertions(+), 42 deletions(-)

diff --git a/src/chat_analyzer.py b/src/chat_analyzer.py
index f9c620d..28cd976 100644
--- a/src/chat_analyzer.py
+++ b/src/chat_analyzer.py
@@ -158,59 +158,49 @@ def import_data(path_to_chatfile: str) -> List[Dict[str, Any]]:
     if isWa:
         print('Whatsapp chat recognized')
         f.seek(0)
-        #To check the dateformats
-        formatdmy = 1
-        formatmdy = 1
-        formatymd = 1
+        date_finalstring = None
         #To check that the date formats in the chat are in which format
-        #Can also check the time format here itself...
         for line in f:
             match = re.search(WMsg, line)
             if match:
                 try:
                     datetime_object = datetime.strptime(match.groupdict()['date'], '%m/%d/%y')
+                    date_string = '%m/%d/%y'
+                    month = 'feild1'
+                    day = 'feild2'
+                    year = 'feild3'
                 except:
-                    formatmdy = 0
-                try:
-                    datetime_object = datetime.strptime(match.groupdict()['date'], '%d/%m/%y')
-                except:
-                    formatdmy = 0
-                try:
-                    datetime_object = datetime.strptime(match.groupdict()['date'], '%y/%m/%d')
-                except:
-                    formatymd = 0    
+                    try:
+                        # If above case is failed,There is chance that this case will also fail.
+                        # Hence we should continue the loop
+                        datetime_object = datetime.strptime(match.groupdict()['date'], '%d/%m/%y')
+                        date_finalstring = '%d/%m/%y'
+                        month = 'feild2'
+                        day = 'feild1'
+                        year = 'feild3'
+                    except:
+                        # If above two cases are failed,String and fields are fixed.
+                        # Hence there is no point in continuing the loop
+                        datetime_object = datetime.strptime(match.groupdict()['date'], '%d/%m/%y')
+                        date_finalstring = '%y/%m/%d'
+                        month = 'feild2'
+                        day = 'feild1'
+                        year = 'feild3'
+                        break
+        # If all lines in the chat satisfies the format m/d/y, therefore assign the string to the final string
+        if date_finalstring is None :
+            date_finalstring = date_string
+
         f.seek(0)
         for line in f:
             match = re.search(WMsg, line)
-            if match and formatmdy:
-                msgs.append({
-                    'username': match.groupdict()['username'],
-                    'date': datetime.strptime(match.groupdict()['date'], '%m/%d/%y').date(),
-                    'month': match.groupdict()['feild1'],
-                    'day': match.groupdict()['feild2'],
-                    'year': match.groupdict()['feild3'],
-                    'time': datetime.strptime(match.groupdict()['time'], '%H:%M').time(),
-                    'hour': match.groupdict()['hour'],
-                    'minute': match.groupdict()['minute'],
-                })
-            elif match and formatdmy:
-                msgs.append({
-                    'username': match.groupdict()['username'],
-                    'date': datetime.strptime(match.groupdict()['date'], '%d/%m/%y').date(),
-                    'month': match.groupdict()['feild2'],
-                    'day': match.groupdict()['feild1'],
-                    'year': match.groupdict()['feild3'],
-                    'time': datetime.strptime(match.groupdict()['time'], '%H:%M').time(),
-                    'hour': match.groupdict()['hour'],
-                    'minute': match.groupdict()['minute'],
-                })
-            elif match and formatymd:
+            if match: 
                 msgs.append({
                     'username': match.groupdict()['username'],
-                    'date': datetime.strptime(match.groupdict()['date'], '%y/%m/%d').date(),
-                    'month': match.groupdict()['feild2'],
-                    'day': match.groupdict()['feild3'],
-                    'year': match.groupdict()['feild1'],
+                    'date':  datetime.strptime(match.groupdict()['date'], date_finalstring).date(),
+                    'month': match.groupdict()[month],
+                    'day': match.groupdict()[day],
+                    'year': match.groupdict()[year],
                     'time': datetime.strptime(match.groupdict()['time'], '%H:%M').time(),
                     'hour': match.groupdict()['hour'],
                     'minute': match.groupdict()['minute'],
diff --git a/tests/test_chats/wa.txt b/tests/test_chats/wa.txt
index b8faa9e..76b57fb 100644
--- a/tests/test_chats/wa.txt
+++ b/tests/test_chats/wa.txt
@@ -39936,4 +39936,4 @@
 3/6/21, 17:28 - D: Test message
 3/6/21, 17:28 - B: Test message
 3/6/21, 17:30 - D: Test message
-3/6/21, 19:07 - C: Test message
+3/6/21, 19:07 - C: Test message
\ No newline at end of file

From 12f16c11504ba1081e888fad44332072084d675c Mon Sep 17 00:00:00 2001
From: sasi <sasi>
Date: Tue, 14 Dec 2021 18:08:25 +0530
Subject: [PATCH 6/8] Date issue Revised 1.2

---
 src/chat_analyzer.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/chat_analyzer.py b/src/chat_analyzer.py
index 28cd976..390abee 100644
--- a/src/chat_analyzer.py
+++ b/src/chat_analyzer.py
@@ -181,7 +181,7 @@ def import_data(path_to_chatfile: str) -> List[Dict[str, Any]]:
                     except:
                         # If above two cases are failed,String and fields are fixed.
                         # Hence there is no point in continuing the loop
-                        datetime_object = datetime.strptime(match.groupdict()['date'], '%d/%m/%y')
+                        datetime_object = datetime.strptime(match.groupdict()['date'], '%y/%m/%d')
                         date_finalstring = '%y/%m/%d'
                         month = 'feild2'
                         day = 'feild1'

From 59c5c78c66eeac3d292f966ecfc4cb3255cb6c81 Mon Sep 17 00:00:00 2001
From: sasi <sasi>
Date: Tue, 14 Dec 2021 18:12:15 +0530
Subject: [PATCH 7/8] Date issue Revised 1.3

---
 src/chat_analyzer.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/chat_analyzer.py b/src/chat_analyzer.py
index 390abee..77320df 100644
--- a/src/chat_analyzer.py
+++ b/src/chat_analyzer.py
@@ -197,7 +197,7 @@ def import_data(path_to_chatfile: str) -> List[Dict[str, Any]]:
             if match: 
                 msgs.append({
                     'username': match.groupdict()['username'],
-                    'date':  datetime.strptime(match.groupdict()['date'], date_finalstring).date(),
+                    'date': datetime.strptime(match.groupdict()['date'], date_finalstring).date(),
                     'month': match.groupdict()[month],
                     'day': match.groupdict()[day],
                     'year': match.groupdict()[year],

From 2c345c99de89b971442f24a31e1eea8c81438c43 Mon Sep 17 00:00:00 2001
From: sasi <sasi>
Date: Tue, 14 Dec 2021 18:29:57 +0530
Subject: [PATCH 8/8] Date issue Revised 1.4

---
 src/chat_analyzer.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/chat_analyzer.py b/src/chat_analyzer.py
index 77320df..f74ba06 100644
--- a/src/chat_analyzer.py
+++ b/src/chat_analyzer.py
@@ -184,8 +184,8 @@ def import_data(path_to_chatfile: str) -> List[Dict[str, Any]]:
                         datetime_object = datetime.strptime(match.groupdict()['date'], '%y/%m/%d')
                         date_finalstring = '%y/%m/%d'
                         month = 'feild2'
-                        day = 'feild1'
-                        year = 'feild3'
+                        day = 'feild3'
+                        year = 'feild1'
                         break
         # If all lines in the chat satisfies the format m/d/y, therefore assign the string to the final string
         if date_finalstring is None :