import re
import openpyxl
from pathlib import Path

def md_to_xlsx(md_path, xlsx_path):
    text = Path(md_path).read_text(encoding="utf-8")

    # 分模块
    modules = re.split(r"=+\s*\n(.+?)\n=+", text, flags=re.S)

    # Excel
    wb = openpyxl.Workbook()
    ws = wb.active
    ws.title = "Coverage Summary"

    # 表头
    headers = [
        "Module",
        "Stmts", "Stmts Covered",
        "Branches", "Branches Covered",
        "FEC Condition Terms", "FEC Condition Terms Covered",
        "FEC Expression Terms", "FEC Expression Terms Covered",
        "States", "States Covered"
    ]
    ws.append(headers)

    metrics = [
        "Stmts",
        "Branches",
        "FEC Condition Terms",
        "FEC Expression Terms",
        "States"
    ]

    # 提取数量与覆盖率
    def extract_from_line(line):
        ints = re.findall(r"(\d+)", line)
        floats = re.findall(r"(\d+\.\d+)", line)
        count = ints[0] if ints else "/"
        covered = (floats[-1] + "%") if floats else "/"
        return count, covered

    # 解析每个模块内容
    for i in range(1, len(modules), 2):
        module = modules[i].strip()
        content = modules[i+1]

        row = [module]

        for metric in metrics:
            m = re.search(rf"^\s*{re.escape(metric)}\b.*$", content, flags=re.M)
            if m:
                cnt, cov = extract_from_line(m.group(0))
            else:
                cnt, cov = "/", "/"
            row.extend([cnt, cov])

        ws.append(row)

    # 自动列宽
    for col in ws.columns:
        max_len = max(len(str(cell.value or "")) for cell in col)
        ws.column_dimensions[col[0].column_letter].width = max(10, min(50, max_len + 2))

    wb.save(xlsx_path)
    print(f"完成转换: {xlsx_path}")


# 示例调用
md_to_xlsx(
    "Coverage Report Summary Data by file.md",
    "coverage_summary.xlsx"
)