Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: a tool to convert json output to SARIF format #16

Merged
merged 8 commits into from
Nov 16, 2022
Merged

feat: a tool to convert json output to SARIF format #16

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
e3a1c72
Create convert_to_sarif.py
justinchuby Nov 10, 2022
c38441e
Update convert_to_sarif.py
justinchuby Nov 10, 2022
92e685b
Create convert_to_sarif_test
justinchuby Nov 10, 2022
ae39775
Rename convert_to_sarif_test to convert_to_sarif_test.py
justinchuby Nov 10, 2022
a860683
Fix severity level
justinchuby Nov 12, 2022
d004e4f
Fix related path
justinchuby Nov 12, 2022
162cdf8
Fix test
justinchuby Nov 12, 2022
4221e5b
Path can be none
justinchuby Nov 12, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
140 changes: 140 additions & 0 deletions tools/convert_to_sarif.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,140 @@
"""Convert the output of lintrunner json to SARIF."""

import argparse
import json
import os
from typing import Iterable


def format_rule_name(lintrunner_result: dict) -> str:
return f"{lintrunner_result['code']}/{lintrunner_result['name']}"


def severity_to_github_level(severity: str) -> str:
if severity in {"advice", "disabled"}:
return "note"
return severity


def parse_single_lintrunner_result(lintrunner_result: dict) -> tuple:
r"""Parse a single lintrunner result.

A result looks like this:
{
"path":"/adapters/pytorch/grep_linter.py",
"line":227,
"char":80,
"code":"FLAKE8",
"severity":"advice",
"name":"E501",
"description":"line too long (81 > 79 characters)\nSee https://www.flake8rules.com/rules/E501.html"
}
"""
if lintrunner_result["path"] is None:
artifact_uri = None
else:
artifact_uri = (
("file://" + lintrunner_result["path"])
if lintrunner_result["path"].startswith("/")
else lintrunner_result["path"]
)
result = {
"ruleId": format_rule_name(lintrunner_result),
"level": severity_to_github_level(lintrunner_result["severity"]),
"message": {
"text": format_rule_name(lintrunner_result)
+ "\n"
+ lintrunner_result["description"],
},
"locations": [
{
"physicalLocation": {
"artifactLocation": {
"uri": artifact_uri,
},
"region": {
"startLine": lintrunner_result["line"] or 1,
"startColumn": lintrunner_result["char"] or 1,
},
},
},
],
}

rule = {
"id": format_rule_name(lintrunner_result),
"rule": {
"id": format_rule_name(lintrunner_result),
"name": format_rule_name(lintrunner_result),
"shortDescription": {
"text": format_rule_name(lintrunner_result)
+ ": "
+ lintrunner_result["description"].split("\n")[0],
},
"fullDescription": {
"text": format_rule_name(lintrunner_result)
+ "\n"
+ lintrunner_result["description"],
},
"defaultConfiguration": {
"level": severity_to_github_level(lintrunner_result["severity"]),
},
},
}

return result, rule


def produce_sarif(lintrunner_results: Iterable[dict]) -> dict:
"""Convert the output of lintrunner json to SARIF."""

rules = {}
results = []
for lintrunner_json in lintrunner_results:
result, rule = parse_single_lintrunner_result(lintrunner_json)
results.append(result)
rules[rule["id"]] = rule["rule"]

sarif = {
"$schema": "https://json.schemastore.org/sarif-2.1.0.json",
"version": "2.1.0",
"runs": [
{
"tool": {
"driver": {
"name": "lintrunner",
"rules": list(rules.values()),
},
},
"results": results,
},
],
}

return sarif


def main(args):
"""Convert the output of lintrunner json to SARIF."""

with open(args.input, "r", encoding="utf-8") as f:
lintrunner_jsons = [json.loads(line) for line in f]

sarif = produce_sarif(lintrunner_jsons)

output_dir = os.path.dirname(args.output)
if output_dir:
os.makedirs(os.path.dirname(args.output), exist_ok=True)

with open(args.output, "w", encoding="utf-8") as f:
json.dump(sarif, f)


if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument(
"--input", type=str, required=True, help="json file generated by lintrunner"
)
parser.add_argument("--output", type=str, required=True, help="output sarif file")
args = parser.parse_args()
main(args)
181 changes: 181 additions & 0 deletions tools/convert_to_sarif_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,181 @@
import unittest

import convert_to_sarif


class TestConvertToSarif(unittest.TestCase):
def test_produce_sarif_returns_correct_sarif_result(self):
lintrunner_results = [
{
"path": "test.py",
"line": 1,
"char": 2,
"code": "FLAKE8",
"severity": "error",
"description": "test description",
"name": "test-code",
},
{
"path": "test.py",
"line": 1,
"char": 2,
"code": "FLAKE8",
"severity": "error",
"description": "test description",
"name": "test-code-2",
},
{
"path": "test2.py",
"line": 3,
"char": 4,
"code": "FLAKE8",
"severity": "advice",
"description": "test description",
"name": "test-code",
},
]
actual = convert_to_sarif.produce_sarif(lintrunner_results)
expected = {
"$schema": "https://json.schemastore.org/sarif-2.1.0.json",
"version": "2.1.0",
"runs": [
{
"tool": {
"driver": {
"name": "lintrunner",
"rules": [
{
"id": "FLAKE8/test-code",
"name": "FLAKE8/test-code",
"shortDescription": {
"text": "FLAKE8/test-code: test description"
},
"fullDescription": {
"text": "FLAKE8/test-code\ntest description"
},
"defaultConfiguration": {"level": "note"},
},
{
"id": "FLAKE8/test-code-2",
"name": "FLAKE8/test-code-2",
"shortDescription": {
"text": "FLAKE8/test-code-2: test description"
},
"fullDescription": {
"text": "FLAKE8/test-code-2\ntest description"
},
"defaultConfiguration": {"level": "error"},
},
],
}
},
"results": [
{
"ruleId": "FLAKE8/test-code",
"level": "error",
"message": {"text": "FLAKE8/test-code\ntest description"},
"locations": [
{
"physicalLocation": {
"artifactLocation": {"uri": "test.py"},
"region": {"startLine": 1, "startColumn": 2},
}
}
],
},
{
"ruleId": "FLAKE8/test-code-2",
"level": "error",
"message": {"text": "FLAKE8/test-code-2\ntest description"},
"locations": [
{
"physicalLocation": {
"artifactLocation": {"uri": "test.py"},
"region": {"startLine": 1, "startColumn": 2},
}
}
],
},
{
"ruleId": "FLAKE8/test-code",
"level": "note",
"message": {"text": "FLAKE8/test-code\ntest description"},
"locations": [
{
"physicalLocation": {
"artifactLocation": {"uri": "test2.py"},
"region": {"startLine": 3, "startColumn": 4},
}
}
],
},
],
}
],
}
self.maxDiff = None
self.assertEqual(actual, expected)

def test_it_handles_relative_paths(self):
lintrunner_results = [
{
"path": "test.py",
"line": 1,
"char": 2,
"code": "FLAKE8",
"severity": "error",
"description": "test description",
"name": "test-code",
},
]
actual = convert_to_sarif.produce_sarif(lintrunner_results)
expected_results = [
{
"ruleId": "FLAKE8/test-code",
"level": "error",
"message": {"text": "FLAKE8/test-code\ntest description"},
"locations": [
{
"physicalLocation": {
"artifactLocation": {"uri": "test.py"},
"region": {"startLine": 1, "startColumn": 2},
}
}
],
},
]
self.assertEqual(actual["runs"][0]["results"], expected_results)

def test_it_handles_absolute_paths(self):
lintrunner_results = [
{
"path": "/path/to/test.py",
"line": 1,
"char": 2,
"code": "FLAKE8",
"severity": "error",
"description": "test description",
"name": "test-code",
},
]
actual = convert_to_sarif.produce_sarif(lintrunner_results)
expected_results = [
{
"ruleId": "FLAKE8/test-code",
"level": "error",
"message": {"text": "FLAKE8/test-code\ntest description"},
"locations": [
{
"physicalLocation": {
"artifactLocation": {"uri": "file:///path/to/test.py"},
"region": {"startLine": 1, "startColumn": 2},
}
}
],
},
]
self.assertEqual(actual["runs"][0]["results"], expected_results)


if __name__ == "__main__":
unittest.main()