langchain/libs/community/tests/integration_tests/utilities/test_outline.py
Bagatur a0c2281540
infra: update mypy 1.10, ruff 0.5 (#23721)
```python
"""python scripts/update_mypy_ruff.py"""
import glob
import tomllib
from pathlib import Path

import toml
import subprocess
import re

ROOT_DIR = Path(__file__).parents[1]


def main():
    for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True):
        print(path)
        with open(path, "rb") as f:
            pyproject = tomllib.load(f)
        try:
            pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = (
                "^1.10"
            )
            pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = (
                "^0.5"
            )
        except KeyError:
            continue
        with open(path, "w") as f:
            toml.dump(pyproject, f)
        cwd = "/".join(path.split("/")[:-1])
        completed = subprocess.run(
            "poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color",
            cwd=cwd,
            shell=True,
            capture_output=True,
            text=True,
        )
        logs = completed.stdout.split("\n")

        to_ignore = {}
        for l in logs:
            if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l):
                path, line_no, error_type = re.match(
                    "^(.*)\:(\d+)\: error:.*\[(.*)\]", l
                ).groups()
                if (path, line_no) in to_ignore:
                    to_ignore[(path, line_no)].append(error_type)
                else:
                    to_ignore[(path, line_no)] = [error_type]
        print(len(to_ignore))
        for (error_path, line_no), error_types in to_ignore.items():
            all_errors = ", ".join(error_types)
            full_path = f"{cwd}/{error_path}"
            try:
                with open(full_path, "r") as f:
                    file_lines = f.readlines()
            except FileNotFoundError:
                continue
            file_lines[int(line_no) - 1] = (
                file_lines[int(line_no) - 1][:-1] + f"  # type: ignore[{all_errors}]\n"
            )
            with open(full_path, "w") as f:
                f.write("".join(file_lines))

        subprocess.run(
            "poetry run ruff format .; poetry run ruff --select I --fix .",
            cwd=cwd,
            shell=True,
            capture_output=True,
            text=True,
        )


if __name__ == "__main__":
    main()

```
2024-07-03 10:33:27 -07:00

118 lines
3.2 KiB
Python

"""Integration test for Outline API Wrapper."""
from typing import List
import pytest
import responses
from langchain_core.documents import Document
from langchain_community.utilities import OutlineAPIWrapper
OUTLINE_INSTANCE_TEST_URL = "https://app.getoutline.com"
OUTLINE_SUCCESS_RESPONSE = {
"data": [
{
"ranking": 0.3911583,
"context": "Testing Context",
"document": {
"id": "abb2bf15-a597-4255-8b19-b742e3d037bf",
"url": "/doc/quick-start-jGuGGGOTuL",
"title": "Test Title",
"text": "Testing Content",
"createdBy": {"name": "John Doe"},
"revision": 3,
"collectionId": "93f182a4-a591-4d47-83f0-752e7bb2065c",
"parentDocumentId": None,
},
},
],
"status": 200,
"ok": True,
}
OUTLINE_EMPTY_RESPONSE = {
"data": [],
"status": 200,
"ok": True,
}
OUTLINE_ERROR_RESPONSE = {
"ok": False,
"error": "authentication_required",
"status": 401,
"message": "Authentication error",
}
@pytest.fixture
def api_client() -> OutlineAPIWrapper:
return OutlineAPIWrapper(
outline_api_key="api_key", outline_instance_url=OUTLINE_INSTANCE_TEST_URL
)
def assert_docs(docs: List[Document], all_meta: bool = False) -> None:
for doc in docs:
assert doc.page_content
assert doc.metadata
main_meta = {"title", "source"}
assert set(doc.metadata).issuperset(main_meta)
if all_meta:
assert len(set(doc.metadata)) > len(main_meta)
else:
assert len(set(doc.metadata)) == len(main_meta)
@responses.activate
def test_run_success(api_client: OutlineAPIWrapper) -> None:
responses.add(
responses.POST,
api_client.outline_instance_url + api_client.outline_search_endpoint, # type: ignore[operator]
json=OUTLINE_SUCCESS_RESPONSE,
status=200,
)
docs = api_client.run("Testing")
assert_docs(docs, all_meta=False)
@responses.activate
def test_run_success_all_meta(api_client: OutlineAPIWrapper) -> None:
api_client.load_all_available_meta = True
responses.add(
responses.POST,
api_client.outline_instance_url + api_client.outline_search_endpoint, # type: ignore[operator]
json=OUTLINE_SUCCESS_RESPONSE,
status=200,
)
docs = api_client.run("Testing")
assert_docs(docs, all_meta=True)
@responses.activate
def test_run_no_result(api_client: OutlineAPIWrapper) -> None:
responses.add(
responses.POST,
api_client.outline_instance_url + api_client.outline_search_endpoint, # type: ignore[operator]
json=OUTLINE_EMPTY_RESPONSE,
status=200,
)
docs = api_client.run("No Result Test")
assert not docs
@responses.activate
def test_run_error(api_client: OutlineAPIWrapper) -> None:
responses.add(
responses.POST,
api_client.outline_instance_url + api_client.outline_search_endpoint, # type: ignore[operator]
json=OUTLINE_ERROR_RESPONSE,
status=401,
)
try:
api_client.run("Testing")
except Exception as e:
assert "Outline API returned an error:" in str(e)