QingLong/AI/Neo4j/K3_Start.py

from K1_KnowledgeGraph import *
from K2_Neo4jExecutor import *


# 切割试题
def split_questions(file_path):
    with open(file_path, 'r', encoding='utf-8') as f:
        content = f.read()

    # 使用正则表达式匹配题目块（包含答案）
    pattern = r'(\d+\.\s+【.*?】.*?(?=\n\d+\.|\Z))'
    questions = re.findall(pattern, content, re.DOTALL)

    # 清洗每个题目块的空白字符
    cleaned_questions = [q.strip() for q in questions]

    return cleaned_questions[:10]  # 确保只返回前10题


if __name__ == '__main__':
    # 清库
    init()

    # 准备执行
    executor = K2_Neo4jExecutor(
        uri=NEO4J_URI,
        auth=NEO4J_AUTH
    )

    # 新增数据库约束（确保节点必须带ID）
    init_script = """
    CREATE CONSTRAINT IF NOT EXISTS FOR (kp:KnowledgePoint) REQUIRE kp.id IS UNIQUE;
    CREATE CONSTRAINT IF NOT EXISTS FOR (ab:AbilityPoint) REQUIRE ab.id IS UNIQUE;
    CREATE CONSTRAINT IF NOT EXISTS FOR (q:Question) REQUIRE q.id IS UNIQUE;
    """
    executor.execute_cypher_text(init_script)
    # 使用示例
    question_blocks = split_questions('ShiTi.md')

    # 验证分割结果
    for i, block in enumerate(question_blocks, 1):
        print(f"第{i}题块：")
        print("-" * 50)
        try:
            kg = KnowledgeGraph(block)
            success, cypher, result = kg.run()
            # 替换一些特殊符号
            cypher = cypher.replace('```neo4j', '').replace('```', '').replace('```cypher', '')
            print(cypher)
            res = executor.execute_cypher_text(cypher)
            print("恭喜，执行数据插入完成！")
        except Exception as e:
            print(f"程序初始化失败: {str(e)}")