mirror of
https://github.com/hwchase17/langchain.git
synced 2025-11-20 12:09:46 +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()
```
89 lines
2.4 KiB
Python
89 lines
2.4 KiB
Python
"""Util that calls bibtexparser."""
|
|
|
|
import logging
|
|
from typing import Any, Dict, List, Mapping
|
|
|
|
from langchain_core.pydantic_v1 import BaseModel, Extra, root_validator
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
OPTIONAL_FIELDS = [
|
|
"annotate",
|
|
"booktitle",
|
|
"editor",
|
|
"howpublished",
|
|
"journal",
|
|
"keywords",
|
|
"note",
|
|
"organization",
|
|
"publisher",
|
|
"school",
|
|
"series",
|
|
"type",
|
|
"doi",
|
|
"issn",
|
|
"isbn",
|
|
]
|
|
|
|
|
|
class BibtexparserWrapper(BaseModel):
|
|
"""Wrapper around bibtexparser.
|
|
|
|
To use, you should have the ``bibtexparser`` python package installed.
|
|
https://bibtexparser.readthedocs.io/en/master/
|
|
|
|
This wrapper will use bibtexparser to load a collection of references from
|
|
a bibtex file and fetch document summaries.
|
|
"""
|
|
|
|
class Config:
|
|
"""Configuration for this pydantic object."""
|
|
|
|
extra = Extra.forbid
|
|
|
|
@root_validator(pre=True)
|
|
def validate_environment(cls, values: Dict) -> Dict:
|
|
"""Validate that the python package exists in environment."""
|
|
try:
|
|
import bibtexparser # noqa
|
|
except ImportError:
|
|
raise ImportError(
|
|
"Could not import bibtexparser python package. "
|
|
"Please install it with `pip install bibtexparser`."
|
|
)
|
|
|
|
return values
|
|
|
|
def load_bibtex_entries(self, path: str) -> List[Dict[str, Any]]:
|
|
"""Load bibtex entries from the bibtex file at the given path."""
|
|
import bibtexparser
|
|
|
|
with open(path) as file:
|
|
entries = bibtexparser.load(file).entries
|
|
return entries
|
|
|
|
def get_metadata(
|
|
self, entry: Mapping[str, Any], load_extra: bool = False
|
|
) -> Dict[str, Any]:
|
|
"""Get metadata for the given entry."""
|
|
publication = entry.get("journal") or entry.get("booktitle")
|
|
if "url" in entry:
|
|
url = entry["url"]
|
|
elif "doi" in entry:
|
|
url = f'https://doi.org/{entry["doi"]}'
|
|
else:
|
|
url = None
|
|
meta = {
|
|
"id": entry.get("ID"),
|
|
"published_year": entry.get("year"),
|
|
"title": entry.get("title"),
|
|
"publication": publication,
|
|
"authors": entry.get("author"),
|
|
"abstract": entry.get("abstract"),
|
|
"url": url,
|
|
}
|
|
if load_extra:
|
|
for field in OPTIONAL_FIELDS:
|
|
meta[field] = entry.get(field)
|
|
return {k: v for k, v in meta.items() if v is not None}
|