mirror of
https://github.com/hwchase17/langchain.git
synced 2025-04-27 11:41:51 +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()
```
52 lines
1.8 KiB
Python
52 lines
1.8 KiB
Python
"""Load Documents from Docusarus Documentation"""
|
|
|
|
from typing import Any, List, Optional
|
|
|
|
from langchain_community.document_loaders.sitemap import SitemapLoader
|
|
|
|
|
|
class DocusaurusLoader(SitemapLoader):
|
|
"""Load from Docusaurus Documentation.
|
|
|
|
It leverages the SitemapLoader to loop through the generated pages of a
|
|
Docusaurus Documentation website and extracts the content by looking for specific
|
|
HTML tags. By default, the parser searches for the main content of the Docusaurus
|
|
page, which is normally the <article>. You can also define your own
|
|
custom HTML tags by providing them as a list, for example: ["div", ".main", "a"].
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
url: str,
|
|
custom_html_tags: Optional[List[str]] = None,
|
|
**kwargs: Any,
|
|
):
|
|
"""Initialize DocusaurusLoader
|
|
|
|
Args:
|
|
url: The base URL of the Docusaurus website.
|
|
custom_html_tags: Optional custom html tags to extract content from pages.
|
|
kwargs: Additional args to extend the underlying SitemapLoader, for example:
|
|
filter_urls, blocksize, meta_function, is_local, continue_on_failure
|
|
"""
|
|
if not kwargs.get("is_local"):
|
|
url = f"{url}/sitemap.xml"
|
|
|
|
self.custom_html_tags = custom_html_tags or ["main article"]
|
|
|
|
super().__init__(
|
|
url,
|
|
parsing_function=kwargs.get("parsing_function") or self._parsing_function,
|
|
**kwargs,
|
|
)
|
|
|
|
def _parsing_function(self, content: Any) -> str:
|
|
"""Parses specific elements from a Docusaurus page."""
|
|
relevant_elements = content.select(",".join(self.custom_html_tags))
|
|
|
|
for element in relevant_elements:
|
|
if element not in relevant_elements:
|
|
element.decompose()
|
|
|
|
return str(content.get_text())
|