Content Filtering › Implementation: Rule-Based PII Filtering

import re
from dataclasses import dataclass
from typing import List, Tuple


@dataclass
class PIIMatch:
    category: str
    matched_text: str
    start: int
    end: int
    replacement: str


# PII pattern registry: maps category name to (regex_pattern, replacement_text)
PII_PATTERNS = {
    "email": (
        r"\b[A-Za-z0-9._%+\-]+@[A-Za-z0-9.\-]+\.[A-Za-z]{2,}\b",
        "[EMAIL REDACTED]",
    ),
    "phone_us": (
        r"\b(?:\+?1[\s.\-]?)?\(?\d{3}\)?[\s.\-]?\d{3}[\s.\-]\d{4}\b",
        "[PHONE REDACTED]",
    ),
    "credit_card": (
        r"\b\d{4}[\s\-]?\d{4}[\s\-]?\d{4}[\s\-]?\d{4}\b",
        "[CARD REDACTED]",
    ),
    "ssn": (r"\b\d{3}-\d{2}-\d{4}\b", "[SSN REDACTED]"),
}


def detect_and_redact_pii(text: str) -> Tuple[str, List[PIIMatch]]:
    """
    Detect PII using regex patterns and return the redacted text plus a list of matches.
    Handles overlapping matches by sorting and applying replacements in order.
    """
    # Collect all matches with their span and category
    raw_matches = []
    for category, (pattern, replacement) in PII_PATTERNS.items():
        for m in re.finditer(pattern, text):
            raw_matches.append(
                (m.start(), m.end(), category, m.group(), replacement)
            )

    # Sort by start position to apply replacements left to right
    raw_matches.sort(key=lambda x: x[0])

    matches = []
    redacted = text
    offset = 0

    for start, end, category, matched_text, replacement in raw_matches:
        adj_start = start + offset
        adj_end = end + offset
        matches.append(
            PIIMatch(
                category=category,
                matched_text=matched_text,
                start=start,
                end=end,
                replacement=replacement,
            )
        )
        redacted = redacted[:adj_start] + replacement + redacted[adj_end:]
        offset += len(replacement) - (end - start)

    return redacted, matches

# Test PII redaction on model outputs
test_outputs = [
    "You can reach me at john.doe@example.com or call 555-867-5309.",
    "Please charge card number 4111-1111-1111-1111 for the order.",
    "My SSN is 123-45-6789 and my email is alice@corp.net.",
    "No sensitive information here, just a normal response.",
]

pii_results = []
for text in test_outputs:
    redacted, matches = detect_and_redact_pii(text)
    pii_results.append((text, redacted, matches))