AIツールに貼り付ける前に氏名・メール・電話番号をマスキングする

Project review notes

Alice Kim asked us to send the revised table to alice.kim@example.com.
If the file is delayed, call Alice at 010-1234-5678.

Bob Lee will review the second draft. His email is bob.lee@example.com and his office number is 02-345-6789.

The final approval should also be checked with A. Kim before Friday.

import csv
import re
import sys
from pathlib import Path

INPUT = Path("message.txt")
OUTPUT_DIR = Path("outputs")
MASKED_FILE = OUTPUT_DIR / "message_masked.txt"
REPORT_FILE = OUTPUT_DIR / "replacements.csv"

KNOWN_NAMES = ["Alice Kim", "Bob Lee"]

EMAIL_RE = re.compile(
    r"\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}\b"
)
PHONE_RE = re.compile(
    r"(?<!\d)(?:010-\d{4}-\d{4}|02-\d{3}-\d{4})(?!\d)"
)


def make_replacer(kind, mapping, rows):
    def replace(match):
        original = match.group(0)
        if original not in mapping:
            placeholder = f"[{kind}_{len(mapping) + 1}]"
            mapping[original] = placeholder
            rows.append(
                {
                    "type": kind,
                    "original": original,
                    "replacement": placeholder,
                }
            )
        return mapping[original]

    return replace


def mask_known_names(text, mapping, rows):
    for name in KNOWN_NAMES:
        if name not in text:
            continue
        if name not in mapping:
            placeholder = f"[NAME_{len(mapping) + 1}]"
            mapping[name] = placeholder
            rows.append(
                {
                    "type": "NAME",
                    "original": name,
                    "replacement": placeholder,
                }
            )
        text = text.replace(name, mapping[name])
    return text


def main():
    if not INPUT.is_file():
        sys.exit(f"Input file not found: {INPUT}")

    if OUTPUT_DIR.exists():
        sys.exit(f"Stop: {OUTPUT_DIR} already exists. Review or rename it first.")

    original = INPUT.read_text(encoding="utf-8")
    rows = []

    name_map = {}
    email_map = {}
    phone_map = {}

    masked = mask_known_names(original, name_map, rows)
    masked = EMAIL_RE.sub(make_replacer("EMAIL", email_map, rows), masked)
    masked = PHONE_RE.sub(make_replacer("PHONE", phone_map, rows), masked)

    OUTPUT_DIR.mkdir()
    MASKED_FILE.write_text(masked, encoding="utf-8")

    with REPORT_FILE.open("x", encoding="utf-8", newline="") as target:
        writer = csv.DictWriter(
            target,
            fieldnames=["type", "original", "replacement"],
        )
        writer.writeheader()
        writer.writerows(rows)

    print(f"Unique names masked: {len(name_map)}")
    print(f"Unique emails masked: {len(email_map)}")
    print(f"Unique phones masked: {len(phone_map)}")
    print(f"Masked copy: {MASKED_FILE}")
    print(f"Replacement report: {REPORT_FILE}")


if __name__ == "__main__":
    main()