From 7688bf91829c95a861b911fa64d197bf20d1ea2c Mon Sep 17 00:00:00 2001
From: Rounak Datta <rounak@commandk.dev>
Date: Thu, 13 Apr 2023 22:18:32 +0530
Subject: [PATCH] WhatsApp document loader - update regex (#2776)

I was testing out the WhatsApp Document loader, and noticed that
sometimes the date is of the following format (notice the additional
underscore):
```
3/24/23, 1:54_PM - +91 99999 99999 joined using this group's invite link
3/24/23, 6:29_PM - +91 99999 99999: When are we starting then?
```

Wierdly, the underscore is visible in Vim, but not on editors like
VSCode. I presume it is some unusual character/line terminator.
Nevertheless, I think handling this edge case will make the document
loader more robust.
---
 .../examples/example_data/whatsapp_chat.txt                | 3 ++-
 langchain/document_loaders/whatsapp_chat.py                | 7 ++++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/docs/modules/indexes/document_loaders/examples/example_data/whatsapp_chat.txt b/docs/modules/indexes/document_loaders/examples/example_data/whatsapp_chat.txt
index 9c88f9bea2..acbe2953e9 100644
--- a/docs/modules/indexes/document_loaders/examples/example_data/whatsapp_chat.txt
+++ b/docs/modules/indexes/document_loaders/examples/example_data/whatsapp_chat.txt
@@ -8,4 +8,5 @@
 1/23/23, 3:02 AM - User 1: I thought you were selling the blue one!
 1/23/23, 3:18 AM - User 2: No Im sorry it was my mistake, the blue one is not for sale
 1/23/23, 3:19 AM - User 1: Oh no worries! Bye
-1/23/23, 3:19 AM - User 2: Bye!
\ No newline at end of file
+1/23/23, 3:19 AM - User 2: Bye!
+1/23/23, 3:22_AM - User 1: And let me know if anything changes
\ No newline at end of file
diff --git a/langchain/document_loaders/whatsapp_chat.py b/langchain/document_loaders/whatsapp_chat.py
index bbe12a6269..2bd1c04a17 100644
--- a/langchain/document_loaders/whatsapp_chat.py
+++ b/langchain/document_loaders/whatsapp_chat.py
@@ -26,9 +26,14 @@ class WhatsAppChatLoader(BaseLoader):
         with open(p, encoding="utf8") as f:
             lines = f.readlines()
 
+        message_line_regex = (
+            r"(\d{1,2}/\d{1,2}/\d{2,4}, "
+            r"\d{1,2}:\d{1,2}[ _]?(?:AM|PM)?) - "
+            r"(.*?): (.*)"
+        )
         for line in lines:
             result = re.match(
-                r"(\d{1,2}/\d{1,2}/\d{2,4}, \d{1,2}:\d{1,2}(?: AM| PM)?) - (.*?): (.*)",
+                message_line_regex,
                 line.strip(),
             )
             if result: