#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import json
import re

def clean_markdown_content(content):
    """清理markdown内容中的删除线和加粗符号"""
    if not content:
        return content
    
    # 删除删除线及其内容 ~~text~~ 
    content = re.sub(r'~~[^~]+~~', '', content)
    
    # 删除中文删除线及其内容 ～～text～～
    content = re.sub(r'～～[^～]+～～', '', content)
    
    # 删除加粗符号但保留内容 **text** -> text
    content = re.sub(r'\*\*([^*]+)\*\*', r'\1', content)
    
    # 删除加粗符号但保留内容 __text__ -> text
    content = re.sub(r'__([^_]+)__', r'\1', content)
    
    # 清理多余的空格和换行
    content = re.sub(r'\n{3,}', '\n\n', content)  # 多个换行变为最多两个
    content = re.sub(r' +', ' ', content)  # 多个空格变为一个
    
    return content.strip()

# 读取数据文件
with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
    content = f.read()

# 提取data对象
import ast
data_start = content.find('const data = {')
data_end = content.rfind('};') + 2
data_str = content[data_start:data_end]

# 解析JSON部分
json_start = data_str.find('{')
json_str = data_str[json_start:]

# 手动解析positions数组，找到有modified字段的岗位
positions_with_modified = [
    "会展策划师",
    "会展讲解员",
    "活动执行",
    "活动策划师",
    "漫展策划师",
    "会展执行助理",
    "旅游规划师",
    "旅游计调专员",
    "景区运营专员",
    "文旅运营总监助理"
]

print("开始清理修改版简历内容...")
print(f"需要清理的岗位: {positions_with_modified}")

# 逐个处理每个岗位
for position_name in positions_with_modified:
    print(f"\n处理岗位: {position_name}")
    
    # 查找该岗位在文件中的位置
    # 使用更精确的模式匹配
    pattern = rf'title:\s*["\']({position_name})["\'].*?content:\s*\{{.*?modified:\s*`([^`]+)`'
    
    matches = list(re.finditer(pattern, content, re.DOTALL))
    
    if matches:
        for match in matches:
            original_modified = match.group(2)
            cleaned_modified = clean_markdown_content(original_modified)
            
            # 替换文件内容
            content = content.replace(
                f"modified: `{original_modified}`",
                f"modified: `{cleaned_modified}`"
            )
            
            print(f"  ✓ 清理了修改版内容")
            print(f"    原长度: {len(original_modified)}")
            print(f"    新长度: {len(cleaned_modified)}")
    else:
        print(f"  ⚠ 未找到该岗位的修改版内容")

# 写回文件
with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
    f.write(content)

print("\n✅ 清理完成！")