import pandas as pd
from pathlib import Path
import re


def find_unnamed_columns(data_dir: str):
    path = Path(data_dir)
    found_issues = False

    print(f"🔍 Scanning {data_dir} for 'Unnamed' columns...\n")

    # 遍历所有 Excel 文件
    for file_path in path.rglob("*.xls*"):
        # 跳过临时文件
        if file_path.name.startswith("~$"):
            continue

        try:
            xls = pd.read_excel(file_path, sheet_name=None)
            for sheet_name, df in xls.items():
                # 检查是否有 Unnamed 列
                unnamed_cols = [c for c in df.columns if "Unnamed" in str(c)]

                if unnamed_cols:
                    found_issues = True
                    print(f"⚠️  File: {file_path} | Sheet: {sheet_name}")
                    print(f"    Found columns: {unnamed_cols}")

                    # 打印前 3 行内容，帮助判断是不是垃圾数据
                    print(f"    Sample content:")
                    print(df[unnamed_cols].head(3).to_string(index=False))
                    print("-" * 40)

        except Exception as e:
            print(f"❌ Error reading {file_path.name}: {e}")

    if not found_issues:
        print("✅ No 'Unnamed' columns found!")


if __name__ == "__main__":
    find_unnamed_columns("data")