"""Defence in depth for guardrail #1 ("only scrubbed text goes to the LLM").

`ScrubbedText` is a `NewType`, i.e. a plain `str` at runtime, so the type checker is the primary guard.
`assert_scrubbed` is a cheap runtime backstop right before text leaves the process: if an obvious
identifier (phone, e-mail, SNILS) is still present, the call to the provider is refused. It is NOT a
replacement for `app.core.privacy.scrub()` — names, addresses etc. are not detected here.
"""

import re

from app.core.types import ScrubbedText

_LEAK_PATTERNS: tuple[re.Pattern[str], ...] = (
    # Russian phone numbers: +7 / 8 followed by 10 digits with optional separators.
    re.compile(r"(?:\+7|(?<!\d)8)[\s\-()]*\d{3}[\s\-()]*\d{3}[\s\-]*\d{2}[\s\-]*\d{2}(?!\d)"),
    re.compile(r"[\w.+-]+@[\w-]+\.[\w.-]+"),
    # SNILS: 123-456-789 01
    re.compile(r"(?<!\d)\d{3}-\d{3}-\d{3}[\s-]\d{2}(?!\d)"),
)


class UnscrubbedTextError(ValueError):
    """Raised when text that looks unscrubbed is about to be sent to the LLM."""


def assert_scrubbed(text: str) -> ScrubbedText:
    for pattern in _LEAK_PATTERNS:
        if pattern.search(text):
            # Never include the text itself in the message: it would end up in logs.
            raise UnscrubbedTextError("identifier pattern found in text bound for LLM")
    return ScrubbedText(text)