onnxruntime/cgmanifests/generate_cgmanifest.py
Justin Chu d834ec895a
Adopt linrtunner as the linting tool - take 2 (#15085)
### Description

`lintrunner` is a linter runner successfully used by pytorch, onnx and
onnx-script. It provides a uniform experience running linters locally
and in CI. It supports all major dev systems: Windows, Linux and MacOs.
The checks are enforced by the `Python format` workflow.

This PR adopts `lintrunner` to onnxruntime and fixed ~2000 flake8 errors
in Python code. `lintrunner` now runs all required python lints
including `ruff`(replacing `flake8`), `black` and `isort`. Future lints
like `clang-format` can be added.

Most errors are auto-fixed by `ruff` and the fixes should be considered
robust.

Lints that are more complicated to fix are applied `# noqa` for now and
should be fixed in follow up PRs.

### Notable changes

1. This PR **removed some suboptimal patterns**:

	- `not xxx in` -> `xxx not in` membership checks
	- bare excepts (`except:` -> `except Exception`)
	- unused imports
	
	The follow up PR will remove:
	
	- `import *`
	- mutable values as default in function definitions (`def func(a=[])`)
	- more unused imports
	- unused local variables

2. Use `ruff` to replace `flake8`. `ruff` is much (40x) faster than
flake8 and is more robust. We are using it successfully in onnx and
onnx-script. It also supports auto-fixing many flake8 errors.

3. Removed the legacy flake8 ci flow and updated docs.

4. The added workflow supports SARIF code scanning reports on github,
example snapshot:
	

![image](https://user-images.githubusercontent.com/11205048/212598953-d60ce8a9-f242-4fa8-8674-8696b704604a.png)

5. Removed `onnxruntime-python-checks-ci-pipeline` as redundant

### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

Unified linting experience in CI and local.

Replacing https://github.com/microsoft/onnxruntime/pull/14306

---------

Signed-off-by: Justin Chu <justinchu@microsoft.com>
2023-03-24 15:29:03 -07:00

208 lines
6.9 KiB
Python

#!/usr/bin/env python3
import argparse
import csv
import json
import os
import re
import subprocess
import sys
from dataclasses import dataclass
from pathlib import PurePosixPath
from urllib.parse import urlparse
import requests
def parse_arguments():
parser = argparse.ArgumentParser()
parser.add_argument("--username", required=True, help="Github username")
parser.add_argument("--token", required=True, help="Github access token")
return parser.parse_args()
args = parse_arguments()
SCRIPT_DIR = os.path.dirname(os.path.realpath(__file__))
REPO_DIR = os.path.normpath(os.path.join(SCRIPT_DIR, ".."))
package_name = None
package_filename = None
package_url = None
registrations = []
@dataclass(frozen=True)
class GitDep:
commit: str
url: str
git_deps = {}
def add_github_dep(name, parsed_url):
segments = parsed_url.path.split("/")
org_name = segments[1]
repo_name = segments[2]
if segments[3] != "archive":
print("unrecognized github url path:" + parsed_url.path)
return
git_repo_url = f"https://github.com/{org_name}/{repo_name}.git"
# For example, the path might be like '/myorg/myrepo/archive/5a5f8a5935762397aa68429b5493084ff970f774.zip'
# The last segment, segments[4], is '5a5f8a5935762397aa68429b5493084ff970f774.zip'
if len(segments) == 5 and re.match(r"[0-9a-f]{40}", PurePosixPath(segments[4]).stem):
commit = PurePosixPath(segments[4]).stem
dep = GitDep(commit, git_repo_url)
if dep not in git_deps:
git_deps[dep] = name
else:
# TODO: support urls like: https://github.com/onnx/onnx-tensorrt/archive/refs/tags/release/7.1.zip
if len(segments) == 5:
tag = PurePosixPath(segments[4]).stem
if tag.endswith(".tar"):
tag = PurePosixPath(tag).stem
elif segments[4] == "refs" and segments[5] == "tags":
tag = PurePosixPath(segments[6]).stem
if tag.endswith(".tar"):
tag = PurePosixPath(tag).stem
else:
print("unrecognized github url path:" + parsed_url.path)
return
# Make a REST call to convert to tag to a git commit
url = f"https://api.github.com/repos/{org_name}/{repo_name}/git/refs/tags/{tag}"
print("requesting %s ..." % url)
res = requests.get(url, auth=(args.username, args.token))
response_json = res.json()
tag_object = response_json["object"]
if tag_object["type"] == "commit":
commit = tag_object["sha"]
elif tag_object["type"] == "tag":
res = requests.get(tag_object["url"], auth=(args.username, args.token))
commit = res.json()["object"]["sha"]
else:
print("unrecognized github url path:" + parsed_url.path)
return
dep = GitDep(commit, git_repo_url)
if dep not in git_deps:
git_deps[dep] = name
with open(
os.path.join(REPO_DIR, "tools", "ci_build", "github", "linux", "docker", "Dockerfile.manylinux2014_cuda11"),
) as f:
for line in f:
if not line.strip():
package_name = None
package_filename = None
package_url = None
if package_filename is None:
m = re.match(r"RUN\s+export\s+(.+?)_ROOT=(\S+).*", line)
if m is not None:
package_name = m.group(1)
package_filename = m.group(2)
else:
m = re.match(r"RUN\s+export\s+(.+?)_VERSION=(\S+).*", line)
if m is not None:
package_name = m.group(1)
package_filename = m.group(2)
elif package_url is None:
m = re.match(r"(.+?)_DOWNLOAD_URL=(\S+)", line)
if m is not None:
package_url = m.group(2)
if package_name == "LIBXCRYPT":
package_url = m.group(2) + "/v" + package_filename + ".tar.gz"
elif package_name == "CMAKE":
package_url = m.group(2) + "/v" + package_filename + "/cmake-" + package_filename + ".tar.gz"
else:
package_url = m.group(2) + "/" + package_filename + ".tar.gz"
parsed_url = urlparse(package_url)
if parsed_url.hostname == "github.com":
add_github_dep("manylinux dependency " + package_name, parsed_url)
else:
registration = {
"Component": {
"Type": "other",
"other": {
"Name": package_name.lower(),
"Version": package_filename.split("-")[-1],
"DownloadUrl": package_url,
},
"comments": "manylinux dependency",
}
}
registrations.append(registration)
package_name = None
package_filename = None
package_url = None
def normalize_path_separators(path):
return path.replace(os.path.sep, "/")
proc = subprocess.run(
[
"git",
"submodule",
"foreach",
"--quiet",
"'{}' '{}' $toplevel/$sm_path".format(
normalize_path_separators(sys.executable),
normalize_path_separators(os.path.join(SCRIPT_DIR, "print_submodule_info.py")),
),
],
check=True,
cwd=REPO_DIR,
capture_output=True,
text=True,
)
submodule_lines = proc.stdout.splitlines()
for submodule_line in submodule_lines:
(absolute_path, url, commit) = submodule_line.split(" ")
git_deps[GitDep(commit, url)] = "git submodule at {}".format(
normalize_path_separators(os.path.relpath(absolute_path, REPO_DIR))
)
with open(os.path.join(SCRIPT_DIR, "..", "cmake", "deps.txt")) as f:
depfile_reader = csv.reader(f, delimiter=";")
for row in depfile_reader:
if len(row) < 3:
continue
name = row[0]
# Lines start with "#" are comments
if name.startswith("#"):
continue
url = row[1]
parsed_url = urlparse(url)
# TODO: add support for gitlab
if parsed_url.hostname == "github.com":
add_github_dep(name, parsed_url)
else:
print("unrecognized url:" + url)
for git_dep, comment in git_deps.items():
registration = {
"component": {
"type": "git",
"git": {
"commitHash": git_dep.commit,
"repositoryUrl": git_dep.url,
},
"comments": comment,
}
}
registrations.append(registration)
cgmanifest = {
"$schema": "https://json.schemastore.org/component-detection-manifest.json",
"Version": 1,
"Registrations": registrations,
}
with open(os.path.join(SCRIPT_DIR, "generated", "cgmanifest.json"), mode="w") as generated_cgmanifest_file:
print(json.dumps(cgmanifest, indent=2), file=generated_cgmanifest_file)