팀 파일명 규칙을 정하고 Python으로 검사하기

YYYYMMDD_project_document_vNN.ext

Example:
20260920_alpha_test-plan_v01.pdf

from pathlib import Path

SOURCE = Path("outputs") / "file_naming_demo"
FILENAMES = [
    "20260920_alpha_test-plan_v01.pdf",
    "20260920_alpha_results_v02.csv",
    "20260921_beta_meeting-notes_v03.txt",
    "20261001_beta_budget_v01.xlsx",
    "2026-09-20_alpha_notes_v01.txt",
    "20260920_Alpha_notes_v01.txt",
    "20260920_alpha_notes_final.txt",
    "20260230_beta_results_v01.csv",
]

SOURCE.parent.mkdir(parents=True, exist_ok=True)
SOURCE.mkdir()  # Stop if the synthetic source already exists.

for filename in FILENAMES:
    target = SOURCE / filename
    with target.open("xb"):
        pass

import csv
import re
from datetime import datetime
from pathlib import Path

SOURCE = Path("outputs") / "file_naming_demo"
OUTPUT_DIR = Path("outputs") / "file_naming_result"
REPORT = OUTPUT_DIR / "file_naming_report.csv"
ALLOWED_EXTENSIONS = {"pdf", "docx", "xlsx", "csv", "txt"}

NAME_PATTERN = re.compile(
    r"^(?P<date>[0-9]{8})_"
    r"(?P<project>[a-z0-9]+(?:-[a-z0-9]+)*)_"
    r"(?P<document>[a-z0-9]+(?:-[a-z0-9]+)*)_"
    r"(?P<version>v[0-9]{2})\."
    r"(?P<extension>[a-z0-9]+)$"
)


def check_filename(filename: str) -> tuple[str, str]:
    match = NAME_PATTERN.fullmatch(filename)
    if match is None:
        return "FAIL", "STRUCTURE_ERROR"

    extension = match.group("extension")
    if extension not in ALLOWED_EXTENSIONS:
        return "FAIL", "UNSUPPORTED_EXTENSION"

    try:
        datetime.strptime(match.group("date"), "%Y%m%d")
    except ValueError:
        return "FAIL", "INVALID_DATE"

    return "PASS", ""


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

    files = sorted(path for path in SOURCE.iterdir() if path.is_file())
    results = []

    for path in files:
        status, issue = check_filename(path.name)
        results.append({
            "filename": path.name,
            "status": status,
            "issue": issue,
        })

    OUTPUT_DIR.parent.mkdir(parents=True, exist_ok=True)
    OUTPUT_DIR.mkdir()
    with REPORT.open("x", encoding="utf-8", newline="") as stream:
        writer = csv.DictWriter(
            stream,
            fieldnames=["filename", "status", "issue"],
        )
        writer.writeheader()
        writer.writerows(results)

    passed = sum(row["status"] == "PASS" for row in results)
    failed = len(results) - passed
    print(f"Files checked: {len(results)}.")
    print(f"Passed: {passed}; failed: {failed}.")
    print(f"Report: {REPORT.as_posix()}")


if __name__ == "__main__":
    main()

python check_file_names.py

Files checked: 8.
Passed: 4; failed: 4.
Report: outputs/file_naming_result/file_naming_report.csv