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/unit_tests/document_loaders/test_mediawikidump.py

49 lines
1.4 KiB
Python

from pathlib import Path
import pytest
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
9 months ago
from langchain_community.document_loaders.mediawikidump import MWDumpLoader
PARENT_DIR = Path(__file__).parent / "sample_documents"
@pytest.mark.requires("mwparserfromhell", "mwxml")
def test_loading_flawed_xml() -> None:
loader = MWDumpLoader((PARENT_DIR / "mwtest_current_pages.xml").absolute())
with pytest.raises(TypeError):
loader.load()
@pytest.mark.requires("mwparserfromhell", "mwxml")
def test_skipping_errors() -> None:
loader = MWDumpLoader(
file_path=(PARENT_DIR / "mwtest_current_pages.xml").absolute(),
stop_on_error=False,
)
documents = loader.load()
assert len(documents) == 3
@pytest.mark.requires("mwparserfromhell", "mwxml")
def test_skipping_redirects() -> None:
loader = MWDumpLoader(
file_path=(PARENT_DIR / "mwtest_current_pages.xml").absolute(),
skip_redirects=True,
stop_on_error=False,
)
documents = loader.load()
assert len(documents) == 2
@pytest.mark.requires("mwparserfromhell", "mwxml")
def test_multiple_namespaces() -> None:
loader = MWDumpLoader(
file_path=(PARENT_DIR / "mwtest_current_pages.xml").absolute(),
namespaces=[0, 6],
skip_redirects=True,
stop_on_error=False,
)
documents = loader.load()
[print(doc) for doc in documents] # noqa: T201
assert len(documents) == 2