fix: message line regex (#196)

martinschaer · mdrxy · faxe1008 · commit ac4a2d9f9543 · 2025-11-06T14:47:03.000+01:00
Tested with a recent backup. Example line:

```
[20/05/2025, 23:58:53] Martin: hello world
```

Co-authored-by: Mason Daugherty &lt;mason@langchain.dev&gt;
diff --git a/libs/community/langchain_community/chat_loaders/whatsapp.py b/libs/community/langchain_community/chat_loaders/whatsapp.py
@@ -38,7 +38,7 @@ def __init__(self, path: str):
             flags=re.IGNORECASE,
         )
         self._message_line_regex = re.compile(
-            r"\u200E*\[?(\d{1,2}/\d{1,2}/\d{2,4}, \d{1,2}:\d{2}:\d{2} (?:AM|PM))\]?[ \u200E]*([^:]+): (.+)",  # noqa
+            r"\u200E*\[?(\d{1,2}\/\d{1,2}\/\d{2,4}, \d{1,2}:\d{2}:\d{2}(?: AM| PM)?)\]?[ \u200E]*([^:]+): (.+)",  # noqa
             flags=re.IGNORECASE,
         )
 

Original file line number	Diff line number	Diff line change
`@@ -38,7 +38,7 @@ def __init__(self, path: str):`
`38`	`38`	`flags=re.IGNORECASE,`
`39`	`39`	`)`
`40`	`40`	`self._message_line_regex = re.compile(`
`41`		`- r"\u200E\[?(\d{1,2}/\d{1,2}/\d{2,4}, \d{1,2}:\d{2}:\d{2} (?:AM\|PM))\]?[ \u200E]([^:]+): (.+)", # noqa`
	`41`	`+ r"\u200E\[?(\d{1,2}\/\d{1,2}\/\d{2,4}, \d{1,2}:\d{2}:\d{2}(?: AM\| PM)?)\]?[ \u200E]([^:]+): (.+)", # noqa`
`42`	`42`	`flags=re.IGNORECASE,`
`43`	`43`	`)`
`44`	`44`