DataOps-platform/scripts/check_node_2272.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
检查节点 2272 的关系
"""

import sys
from pathlib import Path

# 修复 Windows 控制台编码问题
if sys.platform == "win32":
    import io
    sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8")
    sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding="utf-8")

# 添加项目根目录到Python路径
PROJECT_ROOT = Path(__file__).parent.parent
sys.path.insert(0, str(PROJECT_ROOT))

# 设置环境变量以使用 production 配置
import os
from app.config.config import config

if "NEO4J_URI" not in os.environ:
    prod_config = config.get("production")
    if prod_config:
        os.environ["NEO4J_URI"] = prod_config.NEO4J_URI
        os.environ["NEO4J_USER"] = prod_config.NEO4J_USER
        os.environ["NEO4J_PASSWORD"] = prod_config.NEO4J_PASSWORD

from app.services.neo4j_driver import neo4j_driver


def check_node_2272():
    """检查节点 2272 的详细信息"""
    print("=" * 60)
    print("检查节点 2272 的关系")
    print("=" * 60)
    
    with neo4j_driver.get_session() as session:
        # 检查节点 2272 的基本信息
        node_query = """
        MATCH (n)
        WHERE id(n) = 2272
        RETURN n, labels(n) as labels
        """
        result = session.run(node_query)
        record = result.single()
        
        if not record:
            print("节点 2272 不存在")
            return
        
        node = record["n"]
        labels = record["labels"]
        props = dict(node)
        
        print(f"节点ID: 2272")
        print(f"节点类型: {labels}")
        print(f"节点属性: {props.get('name_zh', 'N/A')} ({props.get('name_en', 'N/A')})")
        print()
        
        # 检查所有输出关系（OUTPUT）
        output_query = """
        MATCH (n)-[r:OUTPUT]->(target)
        WHERE id(n) = 2272
        RETURN type(r) as rel_type, id(r) as rel_id, 
               id(target) as target_id, labels(target) as target_labels,
               target.name_zh as target_name_zh, target.name_en as target_name_en
        """
        output_results = session.run(output_query)
        
        output_count = 0
        print("OUTPUT 关系:")
        for record in output_results:
            output_count += 1
            target_id = record["target_id"]
            target_labels = record["target_labels"]
            target_name_zh = record["target_name_zh"] or "N/A"
            target_name_en = record["target_name_en"] or "N/A"
            rel_id = record["rel_id"]
            print(f"  [OUTPUT] 2272 -> {target_id} ({target_labels[0] if target_labels else 'Unknown'}): {target_name_zh} ({target_name_en})")
        
        if output_count == 0:
            print("  没有找到 OUTPUT 关系")
        print()
        
        # 检查所有输入关系（INPUT，反向）
        input_query = """
        MATCH (source)-[r:INPUT]->(n)
        WHERE id(n) = 2272
        RETURN type(r) as rel_type, id(r) as rel_id,
               id(source) as source_id, labels(source) as source_labels,
               source.name_zh as source_name_zh, source.name_en as source_name_en
        """
        input_results = session.run(input_query)
        
        input_count = 0
        print("INPUT 关系（反向）:")
        for record in input_results:
            input_count += 1
            source_id = record["source_id"]
            source_labels = record["source_labels"]
            source_name_zh = record["source_name_zh"] or "N/A"
            source_name_en = record["source_name_en"] or "N/A"
            rel_id = record["rel_id"]
            print(f"  [INPUT] {source_id} ({source_labels[0] if source_labels else 'Unknown'}) -> 2272: {source_name_zh} ({source_name_en})")
        
        if input_count == 0:
            print("  没有找到 INPUT 关系")
        print()


if __name__ == "__main__":
    check_node_2272()