"""PII auto-detection for catalog columns.

When pii_flag is set True, sample_values is forced to None so real PII
never enters LLM prompts. Patterns live in src/security/pii_patterns.py.
"""

from src.security.pii_patterns import EMAIL_REGEX, PHONE_REGEX, PII_NAME_PATTERNS

from .models import Column


class PIIDetector:
    """Marks columns as pii_flag=True when name or sampled values look sensitive.

    Bias is intentional: false positives hide harmless sample values,
    false negatives leak data. When unsure, flag.
    """

    def detect(self, column: Column) -> bool:
        if self._name_matches(column.name):
            return True
        if column.sample_values and self._values_match(column.sample_values):
            return True
        return False

    @staticmethod
    def _name_matches(name: str) -> bool:
        lowered = name.lower()
        return any(pat in lowered for pat in PII_NAME_PATTERNS)

    @staticmethod
    def _values_match(values: list) -> bool:
        for v in values:
            if v is None:
                continue
            s = str(v)
            if EMAIL_REGEX.match(s) or PHONE_REGEX.match(s):
                return True
        return False