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()
```
37 lines
1.2 KiB
Python
37 lines
1.2 KiB
Python
"""Module includes a registry of default parser configurations."""
|
|
|
|
from langchain_community.document_loaders.base import BaseBlobParser
|
|
from langchain_community.document_loaders.parsers.generic import MimeTypeBasedParser
|
|
from langchain_community.document_loaders.parsers.msword import MsWordParser
|
|
from langchain_community.document_loaders.parsers.pdf import PyMuPDFParser
|
|
from langchain_community.document_loaders.parsers.txt import TextParser
|
|
|
|
|
|
def _get_default_parser() -> BaseBlobParser:
|
|
"""Get default mime-type based parser."""
|
|
return MimeTypeBasedParser(
|
|
handlers={
|
|
"application/pdf": PyMuPDFParser(),
|
|
"text/plain": TextParser(),
|
|
"application/msword": MsWordParser(),
|
|
"application/vnd.openxmlformats-officedocument.wordprocessingml.document": (
|
|
MsWordParser()
|
|
),
|
|
},
|
|
fallback_parser=None,
|
|
)
|
|
|
|
|
|
_REGISTRY = {
|
|
"default": _get_default_parser,
|
|
}
|
|
|
|
# PUBLIC API
|
|
|
|
|
|
def get_parser(parser_name: str) -> BaseBlobParser:
|
|
"""Get a parser by parser name."""
|
|
if parser_name not in _REGISTRY:
|
|
raise ValueError(f"Unknown parser combination: {parser_name}")
|
|
return _REGISTRY[parser_name]()
|