github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-07 22:11:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

infra: update mypy 1.10, ruff 0.5 (#23721)

Browse Source 
```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()

```
This commit is contained in:
Bagatur
2024-07-03 13:33:27 -04:00
committed by GitHub
parent 6cd56821dc
commit a0c2281540
915 changed files with 4759 additions and 4047 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
.github/actions/people/app/main.py vendored
View File

@@ -350,11 +350,7 @@ def get_graphql_pr_edges(*, settings: Settings, after: Union[str, None] = None):
print("Querying PRs...")
else:
print(f"Querying PRs with cursor {after}...")
data = get_graphql_response(
settings=settings,
query=prs_query,
after=after
)
data = get_graphql_response(settings=settings, query=prs_query, after=after)
graphql_response = PRsResponse.model_validate(data)
return graphql_response.data.repository.pullRequests.edges
@@ -484,10 +480,16 @@ def get_contributors(settings: Settings):
lines_changed = pr.additions + pr.deletions
score = _logistic(files_changed, 20) + _logistic(lines_changed, 100)
contributor_scores[pr.author.login] += score
three_months_ago = (datetime.now(timezone.utc) - timedelta(days=3*30))
three_months_ago = datetime.now(timezone.utc) - timedelta(days=3 * 30)
if pr.createdAt > three_months_ago:
recent_contributor_scores[pr.author.login] += score
return contributors, contributor_scores, recent_contributor_scores, reviewers, authors
return (
contributors,
contributor_scores,
recent_contributor_scores,
reviewers,
authors,
)
def get_top_users(
@@ -524,9 +526,13 @@ if __name__ == "__main__":
# question_commentors, question_last_month_commentors, question_authors = get_experts(
# settings=settings
# )
contributors, contributor_scores, recent_contributor_scores, reviewers, pr_authors = get_contributors(
settings=settings
)
(
contributors,
contributor_scores,
recent_contributor_scores,
reviewers,
pr_authors,
) = get_contributors(settings=settings)
# authors = {**question_authors, **pr_authors}
authors = {**pr_authors}
maintainers_logins = {
@@ -559,7 +565,7 @@ if __name__ == "__main__":
maintainers.append(
{
"login": login,
"count": contributors[login], #+ question_commentors[login],
"count": contributors[login], # + question_commentors[login],
"avatarUrl": user.avatarUrl,
"twitterUsername": user.twitterUsername,
"url": user.url,
@@ -615,9 +621,7 @@ if __name__ == "__main__":
new_people_content = yaml.dump(
people, sort_keys=False, width=200, allow_unicode=True
)
if (
people_old_content == new_people_content
):
if people_old_content == new_people_content:
logging.info("The LangChain People data hasn't changed, finishing.")
sys.exit(0)
people_path.write_text(new_people_content, encoding="utf-8")
@@ -630,9 +634,7 @@ if __name__ == "__main__":
logging.info(f"Creating a new branch {branch_name}")
subprocess.run(["git", "checkout", "-B", branch_name], check=True)
logging.info("Adding updated file")
subprocess.run(
["git", "add", str(people_path)], check=True
)
subprocess.run(["git", "add", str(people_path)], check=True)
logging.info("Committing updated file")
message = "👥 Update LangChain people data"
result = subprocess.run(["git", "commit", "-m", message], check=True)
@@ -641,4 +643,4 @@ if __name__ == "__main__":
logging.info("Creating PR")
pr = repo.create_pull(title=message, body=message, base="master", head=branch_name)
logging.info(f"Created PR: {pr.number}")
logging.info("Finished")
logging.info("Finished")

27
.github/scripts/check_diff.py vendored
View File

@@ -1,11 +1,12 @@
import glob
import json
import sys
import os
from typing import Dict, List, Set
import re
import sys
import tomllib
from collections import defaultdict
import glob
from typing import Dict, List, Set
LANGCHAIN_DIRS = [
"libs/core",
@@ -15,8 +16,13 @@ LANGCHAIN_DIRS = [
"libs/experimental",
]
def all_package_dirs() -> Set[str]:
return {"/".join(path.split("/")[:-1]) for path in glob.glob("./libs/**/pyproject.toml", recursive=True)}
return {
"/".join(path.split("/")[:-1]).lstrip("./")
for path in glob.glob("./libs/**/pyproject.toml", recursive=True)
if "libs/cli" not in path and "libs/standard-tests" not in path
}
def dependents_graph() -> dict:
@@ -26,9 +32,9 @@ def dependents_graph() -> dict:
if "template" in path:
continue
with open(path, "rb") as f:
pyproject = tomllib.load(f)['tool']['poetry']
pyproject = tomllib.load(f)["tool"]["poetry"]
pkg_dir = "libs" + "/".join(path.split("libs")[1].split("/")[:-1])
for dep in pyproject['dependencies']:
for dep in pyproject["dependencies"]:
if "langchain" in dep:
dependents[dep].add(pkg_dir)
return dependents
@@ -122,9 +128,12 @@ if __name__ == "__main__":
outputs = {
"dirs-to-lint": add_dependents(
dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"],
dependents,
),
"dirs-to-test": add_dependents(
dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
),
"dirs-to-test": add_dependents(dirs_to_run["test"] | dirs_to_run["extended-test"], dependents),
"dirs-to-extended-test": list(dirs_to_run["extended-test"]),
"docs-edited": "true" if docs_edited else "",
}

4
.github/scripts/get_min_versions.py vendored
View File

@@ -74,6 +74,4 @@ if __name__ == "__main__":
# 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()])
)
print(" ".join([f"{lib}=={version}" for lib, version in min_versions.items()]))