[FIX] Restrict end of regex to prevent matches with non-date strings (#…

…136)

* Restrict end of regex to prevent matches with non-date strings

* Add hour and minute to regex to further increase robustness

* Bump version 0.5.3

chatminer/__init__.py

@@ -14,4 +14,4 @@
 # Dev branch marker is: 'X.Y.dev' or 'X.Y.devN' where N is an integer.
 # 'X.Y.dev0' is the canonical version of 'X.Y.dev'
 #
-__version__ = "0.5.2"
+__version__ = "0.5.3"

chatminer/chatparsers.py

@@ -154,7 +154,7 @@ def __init__(self, filepath: str):
 
     def _read_raw_messages_from_file(self):
         def _is_new_message(line: str):
-            regex = r"^[\u200e]?\[?(\d{1,4})([./,-])\d{1,2}\2\d{2,4}([, ])"
+            regex = r"^[\u200e]?\[?(\d{1,4})([./,-])\d{1,2}\2\d{2,4}(?:\s|,\s)(0?\d|1\d|2[0-4]):([0-5]?\d)"
             return re.match(regex, line)
 
         with self._file.open(encoding="utf-8") as f: