llm.py

from presidio_analyzer import AnalyzerEngine

class EnglishDLPAnalyzer:
    def __init__(self):
        self.analyzer = AnalyzerEngine()

    def analyze_text(self, text: str):
        """
        Returns:
            {
                "is_leak": bool,
                "entities": ["EMAIL_ADDRESS", "PHONE_NUMBER", ...]
            }
        """
        if not text or text.strip() == "":
            return {"is_leak": False, "entities": []}

        results = self.analyzer.analyze(text=text, language="en")

        if not results:
            return {"is_leak": False, "entities": []}

        entities = list(set([r.entity_type for r in results]))

        return {
            "is_leak": True,
            "entities": entities
        }