#!/usr/bin/env python3 # -*- coding: utf-8 -*- import json import re import sys def escape_for_js(text): """转义字符串用于JavaScript""" if not text: return "" text = text.replace('\\', '\\\\') text = text.replace('`', '\\`') text = text.replace('${', '\\${') return text def parse_resume_content_complete(resume_content): """ 完整解析简历内容，确保不遗漏任何内容 将内容准确分配到项目经历、专业技能和个人总结三个部分 """ # 清理markdown标题格式，保留原始内容 content = resume_content # 查找三个主要部分 # 项目经历部分 - 从"# 一、项目经历"到"# 二、" project_pattern = r'#\s*一、项目经历(.*?)(?=#\s*二、|$)' project_match = re.search(project_pattern, content, re.DOTALL | re.IGNORECASE) if project_match: project_experience = project_match.group(1).strip() else: # 如果没找到标准格式，尝试其他格式 project_experience = "" # 专业技能部分 - 从"# 二、专业技能"或"# 二、掌握技能"到"# 三、" skills_pattern = r'#\s*二、(?:专业技能|掌握技能)(.*?)(?=#\s*三、|$)' skills_match = re.search(skills_pattern, content, re.DOTALL | re.IGNORECASE) if skills_match: skills = skills_match.group(1).strip() else: skills = "" # 个人总结部分 - 从"# 三、个人总结"或"# 三、个人评价"到结尾 summary_pattern = r'#\s*三、(?:个人总结|个人评价)(.*?)$' summary_match = re.search(summary_pattern, content, re.DOTALL | re.IGNORECASE) if summary_match: personal_summary = summary_match.group(1).strip() else: personal_summary = "" # 如果某个部分没有匹配到，打印警告 if not project_experience: print(f" ⚠️ 警告：未找到项目经历部分") if not skills: print(f" ⚠️ 警告：未找到专业技能部分") if not personal_summary: print(f" ⚠️ 警告：未找到个人总结部分") return { 'projectExperience': project_experience, 'skills': skills, 'personalSummary': personal_summary } def validate_content(position_name, resume_content, parsed_data): """验证解析后的内容是否完整""" original_length = len(resume_content) parsed_length = len(parsed_data['projectExperience']) + \ len(parsed_data['skills']) + \ len(parsed_data['personalSummary']) # 允许一定的差异（因为标题被移除了） if parsed_length < original_length * 0.8: print(f" ⚠️ {position_name}: 可能有内容丢失") print(f" 原始长度: {original_length}, 解析后长度: {parsed_length}") return True def process_part_complete(part_number): """处理指定部分的简历数据，确保内容完整""" file_path = f'/Users/apple/Documents/cursor/教务系统/frontend/网页未导入数据/个人简历内容_part{part_number}.json' print(f"\n========== 处理第 {part_number} 部分 ==========") try: with open(file_path, 'r', encoding='utf-8') as f: data = json.load(f) except FileNotFoundError: print(f"错误：找不到文件 {file_path}") return {} position_map = {} successful_count = 0 failed_positions = [] for item in data: if '❌岗位名称查询' in item and '简历内容' in item: position_name = item['❌岗位名称查询'] resume_content = item['简历内容'] print(f"\n处理岗位: {position_name}") # 解析简历内容 resume_data = parse_resume_content_complete(resume_content) # 验证内容完整性 if validate_content(position_name, resume_content, resume_data): position_map[position_name] = resume_data successful_count += 1 print(f" ✓ 成功解析") else: failed_positions.append(position_name) print(f" ✗ 解析失败") # 保存映射数据 output_file = f'/Users/apple/Documents/cursor/教务系统/frontend/scripts/resume_mapping_part{part_number}.json' with open(output_file, 'w', encoding='utf-8') as f: json.dump(position_map, f, ensure_ascii=False, indent=2) print(f"\n========== 第 {part_number} 部分处理完成 ==========") print(f"成功处理: {successful_count} 个岗位") if failed_positions: print(f"失败岗位: {', '.join(failed_positions)}") print(f"映射数据已保存到: {output_file}") return position_map def find_and_update_position(content, position_name, resume_data): """在mockData.js中查找并更新指定岗位的数据""" updated = False # 尝试多种匹配模式 patterns = [ rf'name:\s*["\']({re.escape(position_name)})["\']', # 标准格式 rf'jobTitle:\s*["\']({re.escape(position_name)})["\']', # jobTitle格式 rf'title:\s*["\']({re.escape(position_name)})["\']', # title格式 ] for pattern in patterns: matches = list(re.finditer(pattern, content)) if matches: for match in matches: print(f" 找到岗位: {position_name} (使用模式: {pattern.split(':')[0]})") # 找到岗位后，查找其resume对象 start_pos = match.start() # 查找resume对象的开始 resume_search_area = content[start_pos:min(start_pos+3000, len(content))] resume_match = re.search(r'resume:\s*\{', resume_search_area) if resume_match: resume_start = start_pos + resume_match.end() # 找到resume对象的结束位置 brace_count = 1 i = resume_start while i < len(content) and brace_count > 0: if content[i] == '{': brace_count += 1 elif content[i] == '}': brace_count -= 1 i += 1 resume_end = i - 1 resume_content = content[resume_start:resume_end] # 检查是否已经有这些字段 if 'projectExperience' not in resume_content: # 在resume对象末尾添加新字段 new_fields = f''', projectExperience: `{escape_for_js(resume_data['projectExperience'])}`, skills: `{escape_for_js(resume_data['skills'])}`, personalSummary: `{escape_for_js(resume_data['personalSummary'])}`''' content = content[:resume_end] + new_fields + content[resume_end:] updated = True print(f" ✓ 更新成功") break else: print(f" - 该岗位已有相关字段，跳过") if updated: break if not updated: print(f" ✗ 未找到岗位: {position_name}") return content, updated def update_mockdata_complete(position_map, part_number): """使用映射数据更新mockData.js，确保内容完整""" print(f"\n========== 开始更新 mockData.js (第 {part_number} 部分) ==========") # 读取当前的mockData.js文件 try: with open('/Users/apple/Documents/cursor/教务系统/frontend/src/data/mockData.js', 'r', encoding='utf-8') as f: content = f.read() except FileNotFoundError: print("错误：找不到 mockData.js 文件") return 0 updated_count = 0 failed_positions = [] # 对每个岗位进行更新 for position_name, resume_data in position_map.items(): print(f"\n更新岗位: {position_name}") # 打印内容长度，便于验证 print(f" 项目经历长度: {len(resume_data['projectExperience'])} 字符") print(f" 专业技能长度: {len(resume_data['skills'])} 字符") print(f" 个人总结长度: {len(resume_data['personalSummary'])} 字符") content, updated = find_and_update_position(content, position_name, resume_data) if updated: updated_count += 1 else: failed_positions.append(position_name) # 写回文件 with open('/Users/apple/Documents/cursor/教务系统/frontend/src/data/mockData.js', 'w', encoding='utf-8') as f: f.write(content) print(f"\n========== 第 {part_number} 部分更新完成 ==========") print(f"成功更新: {updated_count} 个岗位") if failed_positions: print(f"未找到的岗位: {', '.join(failed_positions)}") return updated_count # 主程序 if __name__ == "__main__": if len(sys.argv) > 1: part_num = int(sys.argv[1]) if part_num not in [1, 2, 3]: print("错误：部分编号必须是 1, 2 或 3") sys.exit(1) # 处理指定部分 print(f"开始处理第 {part_num} 部分的简历数据...") position_map = process_part_complete(part_num) if position_map: # 更新mockData.js update_mockdata_complete(position_map, part_num) print(f"\n第 {part_num} 部分处理完成！") else: print(f"\n第 {part_num} 部分没有找到有效数据") else: print("使用方法: python3 update_positions_complete.py <部分编号>") print("部分编号: 1, 2, 或 3") print("\n示例:") print(" python3 update_positions_complete.py 1 # 处理第1部分") print(" python3 update_positions_complete.py 2 # 处理第2部分") print(" python3 update_positions_complete.py 3 # 处理第3部分")