langchain/tests/integration_tests/document_loaders/test_telegram.py
hp0404 374725a715
Refactor TelegramChatLoader and FacebookChatLoader classes and add tests (#3863)
This PR includes two main changes:

- Refactor the `TelegramChatLoader` and `FacebookChatLoader` classes by
removing the dependency on pandas and simplifying the message filtering
process.

- Add test cases for the `TelegramChatLoader` and `FacebookChatLoader`
classes. This test ensures that the class correctly loads and processes
the example chat data, providing better test coverage for this
functionality.
2023-05-03 15:59:19 -07:00

19 lines
632 B
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

from pathlib import Path
from langchain.document_loaders import TelegramChatLoader
def test_telegram_chat_loader() -> None:
"""Test TelegramChatLoader."""
file_path = Path(__file__).parent.parent / "examples/telegram.json"
loader = TelegramChatLoader(str(file_path))
docs = loader.load()
assert len(docs) == 1
assert docs[0].metadata["source"] == str(file_path)
assert docs[0].page_content == (
"Henry on 2020-01-01T00:00:02: It's 2020...\n\n"
"Henry on 2020-01-01T00:00:04: Fireworks!\n\n"
"Grace 🧤 ðŸ\x8d on 2020-01-01T00:00:05: You're a minute late!\n\n"
)