mirror of
https://github.com/Mintplex-Labs/langchain-python.git
synced 2026-08-27 01:15:22 -04:00
Rounak Datta
7688bf9182
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.
46 lines
1.3 KiB
Python
46 lines
1.3 KiB
Python
import re
|
|
from pathlib import Path
|
|
from typing import List
|
|
|
|
from langchain.docstore.document import Document
|
|
from langchain.document_loaders.base import BaseLoader
|
|
|
|
|
|
def concatenate_rows(date: str, sender: str, text: str) -> str:
|
|
"""Combine message information in a readable format ready to be used."""
|
|
return f"{sender} on {date}: {text}\n\n"
|
|
|
|
|
|
class WhatsAppChatLoader(BaseLoader):
|
|
"""Loader that loads WhatsApp messages text file."""
|
|
|
|
def __init__(self, path: str):
|
|
"""Initialize with path."""
|
|
self.file_path = path
|
|
|
|
def load(self) -> List[Document]:
|
|
"""Load documents."""
|
|
p = Path(self.file_path)
|
|
text_content = ""
|
|
|
|
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(
|
|
message_line_regex,
|
|
line.strip(),
|
|
)
|
|
if result:
|
|
date, sender, text = result.groups()
|
|
text_content += concatenate_rows(date, sender, text)
|
|
|
|
metadata = {"source": str(p)}
|
|
|
|
return [Document(page_content=text_content, metadata=metadata)]
|