261 lines
10 KiB
Python
261 lines
10 KiB
Python
#!/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") |