You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/libs/community/tests/integration_tests/document_loaders/test_email.py

36 lines
1.3 KiB
Python

from pathlib import Path
community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463) Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
10 months ago
from langchain_community.document_loaders import (
OutlookMessageLoader,
UnstructuredEmailLoader,
)
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"
)
def test_unstructured_email_loader_with_attachments() -> None:
file_path = Path(__file__).parent.parent / "examples/fake-email-attachment.eml"
loader = UnstructuredEmailLoader(
str(file_path), mode="elements", process_attachments=True
)
docs = loader.load()
assert docs[-1].page_content == "Hey this is a fake attachment!"
assert docs[-1].metadata["filename"] == "fake-attachment.txt"
assert docs[-1].metadata["source"].endswith("fake-email-attachment.eml")