"""Defense-in-depth redaction of secret-like material.

This is a backstop, not the primary control. The primary control is that secret
values are never passed into evidence/log code paths in the first place. Redaction
catches the case where a value leaks into child-process output we control.
"""
from __future__ import annotations

import re
from typing import Iterable

REDACTED = "***REDACTED***"

# Token shapes we proactively mask in child-process output.
_PATTERNS = [
    re.compile(r"npm_[A-Za-z0-9]{8,}"),          # npm automation/publish tokens
    re.compile(r"(?:hv|hvs|hvb|s)\.[A-Za-z0-9._-]{16,}"),  # vault/openbao tokens
    re.compile(r"gh[pousr]_[A-Za-z0-9]{16,}"),    # github tokens
    re.compile(r"xox[baprs]-[A-Za-z0-9-]{10,}"),  # slack tokens
    re.compile(r"AKIA[0-9A-Z]{16}"),              # aws access key id
]


def redact_text(text: str, extra: Iterable[str] = ()) -> str:
    """Mask known token shapes and any caller-supplied literal values."""
    if not text:
        return text
    for literal in extra:
        if literal and len(literal) >= 4:
            text = text.replace(literal, REDACTED)
    for pat in _PATTERNS:
        text = pat.sub(REDACTED, text)
    return text


def looks_secret(name: str) -> bool:
    """Heuristic: does a field/key name suggest it carries a secret value?"""
    lowered = name.lower()
    return any(
        marker in lowered
        for marker in ("token", "secret", "password", "passwd", "apikey", "api_key", "key", "credential")
    )