03-projects/secure-code-scanner/day-002/string_utils.py - master - kremls/python-course-junior

03-projects/secure-code-scanner/day-002/string_utils.py
106 строк2 KB
kremls
day-001 and day-002 done
10 май 2026, 10:27
10 май 2026, 10:273821b62
def normalize_text(value: str | None) -> str:
    if value is None:
        return ""

    return value.strip()


def normalize_severity(value: str | None) -> str:
    return normalize_text(value).upper()


def parse_severity(value: str | None) -> str:
    allowed_values = ("LOW", "MEDIUM", "HIGH", "CRITICAL")
    normalized = normalize_severity(value)

    if normalized in allowed_values:
        return normalized

    return "LOW"


def is_valid_cve(value: str | None) -> bool:
    normalized = normalize_text(value).upper()
    parts = normalized.split("-")

    if len(parts) != 3:
        return False

    prefix, year, number = parts

    if prefix != "CVE":
        return False

    if not year.isdigit() or len(year) != 4:
        return False

    if not number.isdigit() or len(number) < 4:
        return False

    return True


def normalize_cve(value: str | None) -> str:
    normalized = normalize_text(value).upper()

    if is_valid_cve(normalized):
        return normalized

    return ""


def normalize_rule_id(value: str | None) -> str:
    default_value = "PY000"
    normalized = normalize_text(value).upper()

    if len(normalized) != 5:
        return default_value

    prefix = normalized[:2]
    numeric_part = normalized[2:]

    if prefix != "PY":
        return default_value

    if not numeric_part.isdigit():
        return default_value

    return normalized


def sanitize_for_log(value: str | None) -> str:
    normalized = normalize_text(value)

    return (
        normalized
        .replace("\r", "\\r")
        .replace("\n", "\\n")
        .replace("\t", "\\t")
    )


def normalize_line_number(value: int) -> int:
    if value < 1:
        return 1

    return value


def format_finding(
    filename: str,
    line_number: int,
    rule_id: str,
    severity: str,
    message: str,
) -> str:
    safe_filename = sanitize_for_log(filename)
    safe_line_number = normalize_line_number(line_number)
    safe_rule_id = sanitize_for_log(normalize_rule_id(rule_id))
    safe_message = sanitize_for_log(message)
    normalized_severity = parse_severity(severity)

    return (
        f"{safe_filename}:{safe_line_number} "
        f"[{normalized_severity}] "
        f"{safe_rule_id}: {safe_message}"
    )