AIが作成した正規表現を一致・不一致の例でテストする

case_id,value,should_match
C001,WK-2026-0001,yes
C002,WK-2000-0042,yes
C003,WK-2099-9999,yes
C004,WK-1999-0001,no
C005,wk-2026-0001,no
C006,WK-2026-001,no
C007,WK-2026-00001,no
C008,WK-2026_0001,no
C009," WK-2026-0001",no
C010,WK-20A6-0001,no

import csv
import re
from pathlib import Path

SOURCE = Path("regex_cases.csv")
OUTPUT_DIR = Path("outputs") / "regex_check_result"
REPORT = OUTPUT_DIR / "regex_check.csv"

AI_PATTERN = re.compile(r"WK-\d{4}-\d{4}")
REVISED_PATTERN = re.compile(r"WK-20[0-9]{2}-[0-9]{4}")


def parse_expected(value: str) -> bool:
    normalized = value.strip().lower()
    if normalized == "yes":
        return True
    if normalized == "no":
        return False
    raise ValueError(f"Expected yes or no, got: {value!r}")


def label(value: bool) -> str:
    return "MATCH" if value else "NO MATCH"


def main() -> None:
    if not SOURCE.is_file():
        raise FileNotFoundError(f"Source CSV not found: {SOURCE}")
    if OUTPUT_DIR.exists():
        raise FileExistsError(f"Output folder already exists: {OUTPUT_DIR}")

    results = []
    ai_failures = 0
    revised_failures = 0

    with SOURCE.open("r", encoding="utf-8-sig", newline="") as stream:
        reader = csv.DictReader(stream)
        required = {"case_id", "value", "should_match"}
        if reader.fieldnames is None or not required.issubset(reader.fieldnames):
            raise ValueError("CSV is missing a required column.")

        for row_number, row in enumerate(reader, start=2):
            expected = parse_expected(row["should_match"])
            text = row["value"]
            ai_actual = AI_PATTERN.fullmatch(text) is not None
            revised_actual = REVISED_PATTERN.fullmatch(text) is not None
            ai_pass = ai_actual == expected
            revised_pass = revised_actual == expected

            if not ai_pass:
                ai_failures += 1
            if not revised_pass:
                revised_failures += 1

            results.append({
                "case_id": row["case_id"],
                "value": text,
                "expected": label(expected),
                "ai_actual": label(ai_actual),
                "ai_test": "PASS" if ai_pass else "FAIL",
                "revised_actual": label(revised_actual),
                "revised_test": "PASS" if revised_pass else "FAIL",
            })

    OUTPUT_DIR.parent.mkdir(parents=True, exist_ok=True)
    OUTPUT_DIR.mkdir()
    fields = [
        "case_id", "value", "expected", "ai_actual", "ai_test",
        "revised_actual", "revised_test"
    ]
    with REPORT.open("x", encoding="utf-8", newline="") as stream:
        writer = csv.DictWriter(stream, fieldnames=fields)
        writer.writeheader()
        writer.writerows(results)

    print(f"Cases: {len(results)}.")
    print(f"AI pattern failures: {ai_failures}.")
    print(f"Revised pattern failures: {revised_failures}.")
    print(f"Report: {REPORT.as_posix()}")

    if revised_failures:
        raise RuntimeError("Revised pattern still fails one or more tests.")


if __name__ == "__main__":
    main()

python ai_regex_check.py

Cases: 10.
AI pattern failures: 1.
Revised pattern failures: 0.
Report: outputs/regex_check_result/regex_check.csv