Extract_reqs/json_to_excel.py

# -*- coding: utf-8 -*-
"""
将需求JSON文件转换为Excel格式
"""

import json
import argparse
from openpyxl import Workbook
from openpyxl.styles import Font, PatternFill, Alignment, Border, Side
from openpyxl.utils import get_column_letter


def parse_requirements_from_json(json_data, parent_section=""):
    """
    递归解析JSON，提取所有需求
    
    Args:
        json_data: JSON数据（章节或子章节）
        parent_section: 父章节路径
        
    Returns:
        需求列表
    """
    requirements = []
    
    if isinstance(json_data, dict):
        # 提取章节信息
        section_info = json_data.get("章节信息", {})
        section_number = section_info.get("章节编号", "")
        section_title = section_info.get("章节标题", "")
        section_level = section_info.get("章节级别", "")
        
        current_section = f"{section_number} {section_title}".strip() if section_number else section_title
        
        # 提取需求列表
        req_list = json_data.get("需求列表", [])
        for req in req_list:
            req_data = {
                "章节编号": section_number,
                "章节标题": section_title,
                "章节级别": section_level,
                "章节完整路径": current_section,
                "需求类型": req.get("需求类型", ""),
                "需求编号": req.get("需求编号", ""),
                "需求描述": req.get("需求描述", ""),
                "接口名称": req.get("接口名称", ""),
                "接口类型": req.get("接口类型", ""),
                "来源": req.get("来源", ""),
                "目的地": req.get("目的地", "")
            }
            requirements.append(req_data)
        
        # 递归处理子章节
        subsections = json_data.get("子章节", {})
        for subsection_name, subsection_data in subsections.items():
            sub_reqs = parse_requirements_from_json(subsection_data, current_section)
            requirements.extend(sub_reqs)
    
    return requirements


def create_excel(json_file, output_file):
    """
    将JSON文件转换为Excel
    
    Args:
        json_file: 输入的JSON文件路径
        output_file: 输出的Excel文件路径
    """
    # 读取JSON文件
    with open(json_file, 'r', encoding='utf-8') as f:
        data = json.load(f)
    
    # 创建工作簿
    wb = Workbook()
    
    # 创建元数据工作表
    ws_meta = wb.active
    ws_meta.title = "文档元数据"
    
    metadata = data.get("文档元数据", {})
    ws_meta['A1'] = "文档标题"
    ws_meta['B1'] = metadata.get("标题", "")
    ws_meta['A2'] = "生成时间"
    ws_meta['B2'] = metadata.get("生成时间", "")
    ws_meta['A3'] = "总需求数"
    ws_meta['B3'] = metadata.get("总需求数", 0)
    
    # 需求类型统计
    stats = metadata.get("需求类型统计", {})
    row = 5
    ws_meta['A5'] = "需求类型统计"
    ws_meta['A5'].font = Font(bold=True)
    for req_type, count in stats.items():
        row += 1
        ws_meta[f'A{row}'] = req_type
        ws_meta[f'B{row}'] = count
    
    # 设置元数据工作表样式
    for row in ws_meta.iter_rows(min_row=1, max_row=row, min_col=1, max_col=1):
        for cell in row:
            cell.font = Font(bold=True)
            cell.fill = PatternFill(start_color="CCE5FF", end_color="CCE5FF", fill_type="solid")
    
    # 创建需求列表工作表
    ws_reqs = wb.create_sheet(title="需求列表")
    
    # 定义表头（按用户要求的顺序）
    headers = [
        "章节编号", "章节标题", "需求类型", "需求编号", "需求描述",
        "接口名称", "接口类型", "来源", "目的地"
    ]
    
    # 写入表头
    for col, header in enumerate(headers, 1):
        cell = ws_reqs.cell(row=1, column=col, value=header)
        cell.font = Font(bold=True, size=11, color="FFFFFF")
        cell.fill = PatternFill(start_color="4472C4", end_color="4472C4", fill_type="solid")
        cell.alignment = Alignment(horizontal="center", vertical="center")
    
    # 解析所有需求
    all_requirements = []
    need_content = data.get("需求内容", {})
    for section_name, section_data in need_content.items():
        reqs = parse_requirements_from_json(section_data)
        all_requirements.extend(reqs)
    
    # 写入需求数据
    for row_idx, req in enumerate(all_requirements, 2):
        for col_idx, header in enumerate(headers, 1):
            # 获取字段值，如果字段不存在或为空字符串，则为空
            value = req.get(header, "")
            if value is None:
                value = ""
            
            cell = ws_reqs.cell(row=row_idx, column=col_idx, value=value)
            cell.alignment = Alignment(horizontal="left", vertical="top", wrap_text=True)
            
            # 根据需求类型设置颜色
            if header == "需求类型" and value:
                if value == "接口需求":
                    cell.fill = PatternFill(start_color="FFF2CC", end_color="FFF2CC", fill_type="solid")
                elif value == "功能需求":
                    cell.fill = PatternFill(start_color="E2EFDA", end_color="E2EFDA", fill_type="solid")
                else:
                    cell.fill = PatternFill(start_color="FCE4D6", end_color="FCE4D6", fill_type="solid")
    
    # 设置列宽
    column_widths = {
        'A': 12,  # 章节编号
        'B': 25,  # 章节标题
        'C': 12,  # 需求类型
        'D': 18,  # 需求编号
        'E': 80,  # 需求描述
        'F': 25,  # 接口名称
        'G': 25,  # 接口类型
        'H': 25,  # 来源
        'I': 25   # 目的地
    }
    
    for col, width in column_widths.items():
        ws_reqs.column_dimensions[col].width = width
    
    # 设置所有单元格边框
    thin_border = Border(
        left=Side(style='thin'),
        right=Side(style='thin'),
        top=Side(style='thin'),
        bottom=Side(style='thin')
    )
    
    for row in ws_reqs.iter_rows(min_row=1, max_row=len(all_requirements)+1, min_col=1, max_col=len(headers)):
        for cell in row:
            cell.border = thin_border
    
    # 冻结首行
    ws_reqs.freeze_panes = "A2"
    
    # 保存Excel文件
    wb.save(output_file)
    print(f"成功将 {len(all_requirements)} 条需求导出到 Excel 文件: {output_file}")
    print(f"工作表: '文档元数据' - 包含文档基本信息和统计")
    print(f"工作表: '需求列表' - 包含所有需求的详细信息")


def main():
    parser = argparse.ArgumentParser(description='将需求JSON文件转换为Excel格式')
    parser.add_argument('-i', '--input', required=True, help='输入的JSON文件路径')
    parser.add_argument('-o', '--output', required=True, help='输出的Excel文件路径')
    
    args = parser.parse_args()
    
    try:
        create_excel(args.input, args.output)
    except Exception as e:
        print(f"转换失败: {e}")
        import traceback
        traceback.print_exc()


if __name__ == "__main__":
    main()