Convert pylint output to simplified CodeClimate JSON suitable for Gitlab Code Quality checks

pylint_to_gitlab_codeclimate.py

import hashlib
import json
import sys
from typing import TYPE_CHECKING, Optional

from pylint.interfaces import IReporter
from pylint.reporters import JSONReporter
from pylint.lint import Run
from pylint.message import Message

if TYPE_CHECKING:
    from pylint.reporters.ureports.nodes import Section

# map pylint categories to CodeClimate severity
PYLINT_CATEGORY_TO_SEVERITY = {
    "fatal": "blocker",
    "error": "critical",
    "warning": "major",
    "refactor": "minor",
    "convention": "minor",
}


class GitlabCodeClimateReporter(JSONReporter):
    """
    Custom pylint reporter to convert pylint messages into a reduced CodeClimate JSON report
    suitable for Gitlab's Code Quality. Only reports `description`, `fingerprint`, `severity`,
    `location`.

    See:
    1. https://docs.gitlab.com/ee/user/project/merge_requests/code_quality.html#implementing-a-custom-tool.
    2. https://github.com/PyCQA/pylint/blob/master/pylint/reporters/json_reporter.py

    Small portions taken from https://github.com/mercos/codeclimate-pylint where no copyright or
    license was asserted as of February 2020
    """

    __implements__ = IReporter
    name = "gitlabcodeclimate"

    def display_messages(self, layout: Optional["Section"]) -> None:
        """Launch layouts display"""
        json_dumpable = [
            {
                "description": msg["description"],
                "severity": msg["severity"],
                "location": msg["location"],
                "fingerprint": msg["fingerprint"]
            }
            for msg in self.messages
        ]
        print(json.dumps(json_dumpable, indent=4), file=self.out)

    def handle_message(self, msg: Message):
        """
        Convert a pylint Message into a reduced CodeClimate report dictionary and append to the messages list.
        """
        codeclimate_dict = dict()

        message_lines = self._parse_message(msg.msg).splitlines()
        codeclimate_dict["description"] = message_lines[0]
        codeclimate_dict["severity"] = PYLINT_CATEGORY_TO_SEVERITY[msg.category]

        # gitlab only uses the "lines.begin" version of location
        codeclimate_dict["location"] = {"path": msg.path, "lines": {"begin": msg.line}}

        # gitlab needs a fingerprint
        # hash the issue, filename and line number
        codeclimate_dict["fingerprint"] = hashlib.sha1(
            (msg.symbol + msg.path + str(msg.line)).encode()
        ).hexdigest()

        self.messages.append(codeclimate_dict)

    def _parse_message(self, msg: str):
        """ Helper to cleanup the message string. """
        while "  " in msg:
            msg = msg.replace("  ", " ")
        msg = msg.replace('"', "`")
        msg = msg.replace("\\", "")
        return msg


if __name__ == "__main__":
    Run(sys.argv[1:], reporter=GitlabCodeClimateReporter())