mirror of
https://github.com/hwchase17/langchain.git
synced 2026-01-24 05:50:18 +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()
```
78 lines
2.3 KiB
Python
78 lines
2.3 KiB
Python
import sys
|
|
|
|
import tomllib
|
|
from packaging.version import parse as parse_version
|
|
import re
|
|
|
|
MIN_VERSION_LIBS = [
|
|
"langchain-core",
|
|
"langchain-community",
|
|
"langchain",
|
|
"langchain-text-splitters",
|
|
]
|
|
|
|
|
|
def get_min_version(version: str) -> str:
|
|
# base regex for x.x.x with cases for rc/post/etc
|
|
# valid strings: https://peps.python.org/pep-0440/#public-version-identifiers
|
|
vstring = r"\d+(?:\.\d+){0,2}(?:(?:a|b|rc|\.post|\.dev)\d+)?"
|
|
# case ^x.x.x
|
|
_match = re.match(f"^\\^({vstring})$", version)
|
|
if _match:
|
|
return _match.group(1)
|
|
|
|
# case >=x.x.x,<y.y.y
|
|
_match = re.match(f"^>=({vstring}),<({vstring})$", version)
|
|
if _match:
|
|
_min = _match.group(1)
|
|
_max = _match.group(2)
|
|
assert parse_version(_min) < parse_version(_max)
|
|
return _min
|
|
|
|
# case x.x.x
|
|
_match = re.match(f"^({vstring})$", version)
|
|
if _match:
|
|
return _match.group(1)
|
|
|
|
raise ValueError(f"Unrecognized version format: {version}")
|
|
|
|
|
|
def get_min_version_from_toml(toml_path: str):
|
|
# Parse the TOML file
|
|
with open(toml_path, "rb") as file:
|
|
toml_data = tomllib.load(file)
|
|
|
|
# Get the dependencies from tool.poetry.dependencies
|
|
dependencies = toml_data["tool"]["poetry"]["dependencies"]
|
|
|
|
# Initialize a dictionary to store the minimum versions
|
|
min_versions = {}
|
|
|
|
# Iterate over the libs in MIN_VERSION_LIBS
|
|
for lib in MIN_VERSION_LIBS:
|
|
# Check if the lib is present in the dependencies
|
|
if lib in dependencies:
|
|
# Get the version string
|
|
version_string = dependencies[lib]
|
|
|
|
if isinstance(version_string, dict):
|
|
version_string = version_string["version"]
|
|
|
|
# Use parse_version to get the minimum supported version from version_string
|
|
min_version = get_min_version(version_string)
|
|
|
|
# Store the minimum version in the min_versions dictionary
|
|
min_versions[lib] = min_version
|
|
|
|
return min_versions
|
|
|
|
|
|
if __name__ == "__main__":
|
|
# Get the TOML file path from the command line argument
|
|
toml_file = sys.argv[1]
|
|
|
|
# Call the function to get the minimum versions
|
|
min_versions = get_min_version_from_toml(toml_file)
|
|
|
|
print(" ".join([f"{lib}=={version}" for lib, version in min_versions.items()]))
|