github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-23 15:19:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix whatsappchatloader - enable parsing new datetime format on WhatsApp chat (#6555)

Browse Source 
- Description: observed new format on WhatsApp exported chat - example:
`[2023/5/4, 16:17:13] ~ Carolina: 🥺`
  - Dependencies: no additional dependencies required
  - Tag maintainer: @rlancemartin, @eyurtsev
This commit is contained in:
Suri Chen 2023-06-21 22:11:49 -04:00 committed by GitHub
parent 5322bac5fc
commit 14b9418cc5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
langchain/document_loaders/whatsapp_chat.py
View File

@ -29,11 +29,11 @@ class WhatsAppChatLoader(BaseLoader):
message_line_regex = r"""
\[?
(
\d{1,2}
\d{1,4}
[\/.]
\d{1,2}
[\/.]
\d{2,4}
\d{1,4}
,\s
\d{1,2}
:\d{2}

1
tests/integration_tests/document_loaders/test_whatsapp_chat.py
View File

@ -17,4 +17,5 @@ def test_whatsapp_chat_loader() -> None:
"User 2 on 1/23/23, 3:19 AM: Bye!\n\n"
"User 1 on 1/23/23, 3:22_AM: And let me know if anything changes\n\n"
"~ User name 2 on 1/24/21, 12:41:03 PM: Of course!\n\n"
"~ User 2 on 2023/5/4, 16:13:23: See you!\n\n"
)

3
tests/integration_tests/examples/whatsapp_chat.txt
View File

@ -2,4 +2,5 @@
[11/8/21, 9:41:32 AM] User name: Message 123
1/23/23, 3:19 AM - User 2: Bye!
1/23/23, 3:22_AM - User 1: And let me know if anything changes
[1/24/21, 12:41:03 PM] ~ User name 2: Of course!
[1/24/21, 12:41:03 PM] ~ User name 2: Of course!
[2023/5/4, 16:13:23] ~ User 2: See you!