messyscript/convert2one.py

#将高考题md文档分割成单独的题目

import re
import os

def parse_document(content):
    """
    解析文档内容，提取所有题目和对应的答案详解
    """
    # 分割题目部分和答案部分
    parts = content.split("**《2024年新课标全国Ⅰ卷数学真题》参考答案**")

    if len(parts) < 2:
        return []

    questions_part = parts[0]
    answers_part = parts[1]

    # 提取所有题目
    questions = extract_questions(questions_part)

    # 提取所有答案
    answers = extract_answers(answers_part)

    # 合并题目和答案
    result = []
    for i, (q_num, q_content) in enumerate(questions):
        if i < len(answers):
            result.append((q_num, q_content, answers[i][1]))

    return result

def extract_questions(content):
    """
    从题目部分提取所有题目
    """
    questions = []

    # 匹配题目的正则表达式（匹配 "数字．" 格式）
    pattern = r'(\d+)．(.*?)(?=\d+．|$)'
    matches = re.finditer(pattern, content, re.DOTALL)

    for match in matches:
        question_num = match.group(1)
        question_content = match.group(2).strip()
        questions.append((question_num, question_content))

    return questions

def extract_answers(content):
    """
    从答案部分提取所有答案详解
    """
    answers = []

    # 匹配答案的正则表达式
    pattern = r'(\d+)．(.*?)(?=\d+．|$)'
    matches = re.finditer(pattern, content, re.DOTALL)

    for match in matches:
        answer_num = match.group(1)
        answer_content = match.group(2).strip()

        # 清理答案内容，移除开头的选项字母
        answer_content = re.sub(r'^[A-D]', '', answer_content).strip()
        answers.append((answer_num, answer_content))

    return answers

def get_question_type(question_num):
    """
    根据题号确定题目类型
    """
    num = int(question_num)
    if 1 <= num <= 8:
        return "单选"
    elif 9 <= num <= 11:
        return "多选"
    elif 12 <= num <= 14:
        return "填空"
    else:
        return "解答"

def format_question_md(question_num, question_content, answer_content):
    """
    格式化单个题目为Markdown格式，答案用callouts隐藏
    """
    question_type = get_question_type(question_num)

    # 添加元数据
    metadata = f"""---
Tags:
  - 题库
年份: 2024
源卷: 全国1
原题号: {question_num}
题目类型: {question_type}
知识点:
  -
难度:
---

"""

    # 处理答案内容，每一行都加上 > 前缀
    formatted_answer = ""
    for line in answer_content.split('\n'):
        if line.strip():  # 非空行
            formatted_answer += f"> {line}\n"
        else:  # 空行
            formatted_answer += ">\n"

    md_content = f"""{metadata}# 第{question_num}题

## 题目

{question_content}

## 答案

> [!question]- 点击查看答案
{formatted_answer}
"""
    return md_content

def save_questions(questions_data, output_dir="questions"):
    """
    保存所有题目为单独的Markdown文件
    """
    if not os.path.exists(output_dir):
        os.makedirs(output_dir)

    for question_num, question_content, answer_content in questions_data:
        filename = f"{question_num}.md"
        filepath = os.path.join(output_dir, filename)

        md_content = format_question_md(question_num, question_content, answer_content)

        with open(filepath, 'w', encoding='utf-8') as f:
            f.write(md_content)

        print(f"已保存: {filename}")

def main():
    # 读取文档内容（这里使用文档2的内容）
    with open('document2.txt', 'r', encoding='utf-8') as f:
        content = f.read()

    # 解析文档
    questions_data = parse_document(content)

    if not questions_data:
        print("未能解析出题目数据")
        return

    print(f"成功解析 {len(questions_data)} 道题目")

    # 保存为单独的Markdown文件
    save_questions(questions_data)

if __name__ == "__main__":
    main()