langchain/tests/integration_tests/document_loaders/test_telegram.py
Harrison Chase 12b4ee1fc7
Harrison/telegram chat loader (#4698)
Co-authored-by: Akinwande Komolafe <47945512+Sensei-akin@users.noreply.github.com>
Co-authored-by: Akinwande Komolafe <akhinoz@gmail.com>
2023-05-14 22:04:27 -07:00

19 lines
645 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 TelegramChatFileLoader
def test_telegram_chat_file_loader() -> None:
"""Test TelegramChatLoader."""
file_path = Path(__file__).parent.parent / "examples/telegram.json"
loader = TelegramChatFileLoader(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"
)