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_gitbook.py

57 lines
1.8 KiB
Python

from typing import Optional
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
10 months ago
from langchain_community.document_loaders.gitbook import GitbookLoader
class TestGitbookLoader:
@pytest.mark.parametrize(
"web_page, load_all_paths, base_url, expected_web_path",
[
("https://example.com/page1", False, None, "https://example.com/page1"),
(
"https://example.com/",
True,
"https://example.com",
"https://example.com/sitemap.xml",
),
],
)
def test_init(
self,
web_page: str,
load_all_paths: bool,
base_url: Optional[str],
expected_web_path: str,
) -> None:
loader = GitbookLoader(
web_page, load_all_paths=load_all_paths, base_url=base_url
)
print(loader.__dict__)
assert (
loader.base_url == (base_url or web_page)[:-1]
if (base_url or web_page).endswith("/")
else (base_url or web_page)
)
assert loader.web_path == expected_web_path
assert loader.load_all_paths == load_all_paths
@pytest.mark.parametrize(
"web_page, expected_number_results",
[("https://platform-docs.opentargets.org/getting-started", 1)],
)
def test_load_single_page(
self, web_page: str, expected_number_results: int
) -> None:
loader = GitbookLoader(web_page)
result = loader.load()
assert len(result) == expected_number_results
@pytest.mark.parametrize("web_page", [("https://platform-docs.opentargets.org/")])
def test_load_multiple_pages(self, web_page: str) -> None:
loader = GitbookLoader(web_page, load_all_paths=True)
result = loader.load()
print(len(result))
assert len(result) > 10