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

import os
import re

def read_ehs_content():
    """
    读取EHS项目文件并按章节拆分
    """
    project_folder = "网页未导入数据/能源产业/学生完成的项目"

    for file in os.listdir(project_folder):
        if "EHS" in file and file.endswith(".md"):
            file_path = os.path.join(project_folder, file)
            with open(file_path, 'r', encoding='utf-8') as f:
                content = f.read()
            return content, file.replace(".md", "")
    return None, None

def parse_sections(content):
    """
    解析markdown内容，按一级标题拆分成多个板块
    """
    # 按 # 一级标题拆分内容
    sections = []

    # 使用正则表达式找到所有一级标题
    pattern = r'^# (.+?)$'
    lines = content.split('\n')

    current_section = None
    current_content = []

    for line in lines:
        match = re.match(pattern, line)
        if match:
            # 保存前一个section
            if current_section:
                sections.append({
                    'title': current_section,
                    'content': '\n'.join(current_content).strip()
                })
            # 开始新的section
            current_section = match.group(1).strip().replace('"', "'")
            current_content = []
        else:
            if current_section:  # 只有在有当前section时才添加内容
                current_content.append(line)

    # 保存最后一个section
    if current_section:
        sections.append({
            'title': current_section,
            'content': '\n'.join(current_content).strip()
        })

    return sections

def generate_sections_code():
    """
    生成正确格式的sections数组
    """
    content, title = read_ehs_content()
    if not content:
        print("未找到EHS项目文件")
        return

    sections = parse_sections(content)

    # 生成JavaScript代码
    js_code = '        sections: [\n'

    for i, section in enumerate(sections):
        # 转义特殊字符
        content_escaped = section['content'].replace('\\', '\\\\').replace('`', '\\`').replace('${', '\\${')

        js_code += '          {\n'
        js_code += f'            title: "{section["title"]}",\n'
        js_code += f'            content: `{content_escaped}`\n'
        js_code += '          }'

        if i < len(sections) - 1:
            js_code += ','
        js_code += '\n'

    js_code += '        ]'

    # 保存到文件
    with open("ehs_sections_fix.js", 'w', encoding='utf-8') as f:
        f.write(js_code)

    print(f"✅ 已生成修复后的sections代码")
    print(f"📊 共拆分为 {len(sections)} 个板块：")
    for section in sections:
        print(f"   - {section['title']}")

if __name__ == "__main__":
    generate_sections_code()