mirror of
https://github.com/hwchase17/langchain
synced 2024-11-11 19:11:02 +00:00
a0c2281540
```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()
```
57 lines
1.6 KiB
Python
57 lines
1.6 KiB
Python
"""Integration test for Wikipedia Document Loader."""
|
|
|
|
from typing import List
|
|
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.document_loaders import WikipediaLoader
|
|
|
|
|
|
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", "summary", "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)
|
|
|
|
|
|
def test_load_success() -> None:
|
|
loader = WikipediaLoader(query="HUNTER X HUNTER")
|
|
docs = loader.load()
|
|
assert len(docs) > 1
|
|
assert len(docs) <= 25
|
|
assert_docs(docs, all_meta=False)
|
|
|
|
|
|
def test_load_success_all_meta() -> None:
|
|
load_max_docs = 5
|
|
load_all_available_meta = True
|
|
loader = WikipediaLoader(
|
|
query="HUNTER X HUNTER",
|
|
load_max_docs=load_max_docs,
|
|
load_all_available_meta=load_all_available_meta,
|
|
)
|
|
docs = loader.load()
|
|
assert len(docs) == load_max_docs
|
|
assert_docs(docs, all_meta=load_all_available_meta)
|
|
|
|
|
|
def test_load_success_more() -> None:
|
|
load_max_docs = 10
|
|
loader = WikipediaLoader(query="HUNTER X HUNTER", load_max_docs=load_max_docs)
|
|
docs = loader.load()
|
|
assert len(docs) == load_max_docs
|
|
assert_docs(docs, all_meta=False)
|
|
|
|
|
|
def test_load_no_result() -> None:
|
|
loader = WikipediaLoader(
|
|
"NORESULTCALL_NORESULTCALL_NORESULTCALL_NORESULTCALL_NORESULTCALL_NORESULTCALL"
|
|
)
|
|
docs = loader.load()
|
|
assert not docs
|