Harrison/msg files (#2375)

Co-authored-by: Sahil Masand <masand.sahil@gmail.com>
Co-authored-by: Sahil Masand <masands@cbh.com.au>
This commit is contained in:
Harrison Chase
2023-04-04 06:48:34 -07:00
committed by GitHub
parent 585f60a5aa
commit e90d007db3
6 changed files with 143 additions and 6 deletions

View File

@@ -0,0 +1,20 @@
from pathlib import Path
from langchain.document_loaders import OutlookMessageLoader
def test_outlook_message_loader() -> None:
"""Test OutlookMessageLoader."""
file_path = Path(__file__).parent.parent / "examples/hello.msg"
loader = OutlookMessageLoader(str(file_path))
docs = loader.load()
assert len(docs) == 1
assert docs[0].metadata["subject"] == "Test for TIF files"
assert docs[0].metadata["sender"] == "Brian Zhou <brizhou@gmail.com>"
assert docs[0].metadata["date"] == "Mon, 18 Nov 2013 16:26:24 +0800"
assert docs[0].page_content == (
"This is a test email to experiment with the MS Outlook MSG "
"Extractor\r\n\r\n\r\n-- \r\n\r\n\r\nKind regards"
"\r\n\r\n\r\n\r\n\r\nBrian Zhou\r\n\r\n"
)

Binary file not shown.