02-lessons/day-003/task.py - master - kremls/python-course-junior

02-lessons/day-003/task.py
143 строки3 KB
kremls
done day-004
16 май 2026, 15:30
16 май 2026, 15:309681412
ALLOWED_SEVERITIES = {"LOW", "MEDIUM", "HIGH", "CRITICAL"}


def normalize_string(value: object, max_length: int = 200) -> str:
    if not isinstance(value, str):
        return ""

    return value.strip()[:max_length]


def normalize_line(value: object) -> int:
    if not isinstance(value, int):
        return 0

    if value < 1:
        return 0

    return value


def normalize_severity(value: object) -> str:
    if not isinstance(value, str):
        return "LOW"

    normalized = value.strip().upper()

    if normalized in ALLOWED_SEVERITIES:
        return normalized

    return "LOW"


def normalize_finding(raw_finding: dict) -> dict:
    return {
        "file": normalize_string(raw_finding.get("file")),
        "line": normalize_line(raw_finding.get("line")),
        "rule_id": normalize_string(raw_finding.get("rule_id")),
        "severity": normalize_severity(raw_finding.get("severity")),
    }


def create_finding(file: str, line: int, rule_id: str, severity: str) -> dict:
    return normalize_finding({
        "file": file,
        "line": line,
        "rule_id": rule_id,
        "severity": severity,
    })


def deduplicate_findings(findings: list[dict]) -> list[dict]:
    seen = set()
    result = []

    for finding in findings:
        identity = (
            finding["file"],
            finding["line"],
            finding["rule_id"],
        )

        if identity in seen:
            continue

        seen.add(identity)
        result.append(finding)

    return result


def normalize_findings(raw_findings: list[dict]) -> list[dict]:
    normalized = []

    for raw_finding in raw_findings:
        if not isinstance(raw_finding, dict):
            continue

        normalized.append(normalize_finding(raw_finding))

    return deduplicate_findings(normalized)


def count_by_severity(findings: list[dict]) -> dict:
    stats = {
        "LOW": 0,
        "MEDIUM": 0,
        "HIGH": 0,
        "CRITICAL": 0,
    }

    for finding in findings:
        severity = normalize_severity(finding.get("severity"))
        stats[severity] += 1

    return stats


def get_unique_rule_ids(findings: list[dict]) -> set[str]:
    result = set()

    for finding in findings:
        rule_id = normalize_string(finding.get("rule_id"))

        if rule_id:
            result.add(rule_id)

    return result


def main():
    raw_findings = [
        create_finding("app.py", 11, "SQL_INJECTION", "HIGH"),
        create_finding("app.py", 12, "LOG_FORGING", "MEDIUM"),
        create_finding("app.py", 14, "DUPLICATE", "LOW"),
        create_finding("app.py", 15, "XSS", "HIGH"),
        create_finding("app.py", 11, "SQL_INJECTION", "HIGH"),
        {"file": " bad.py ", "line": -10, "rule_id": " SSRF ", "severity": "critical"},
        "invalid finding",
        None,
    ]

    findings = normalize_findings(raw_findings)

    print("High risk findings:")
    for finding in findings:
        if finding.get("severity") in {"HIGH", "CRITICAL"}:
            print(finding)

    print("Total findings:")
    print(len(findings))

    print("Unique rule ids:")
    print(get_unique_rule_ids(findings))

    print("Stats by severity:")
    print(count_by_severity(findings))

    print("Normalized and deduplicated findings:")
    print(findings)


if __name__ == "__main__":
    main()