neo4j 图表数据导入到 TuGraph

前言:近期在引入阿里的 TuGraph 图数据库，需要将 原 neo4j 数据导入到新的 tugraph 数据库中。预期走csv文件导入导出，但因为格式和数据库设计问题，操作起来比较麻烦（可能是个人没有发现其他比较方便的办法），因此写了一个 python 脚本进行数据导入操作。

使用：python3,TuGraph 4.5.1

遇到的问题：tugraph 的节点需要一个主键，这个只能自行指定。

支持：指定节点，指定边。自动创建不存在的节点/边，数据导入批量导入节点，单条导入边（试过批量的，tugraph好像不支持 官网的 CALL db.upsertEdge 我的版本也还没实现）。

导入图示:

代码文件

# import time
import json
from typing import Dict, List, cast


class GraphConnector():
    db_type: str = "tugraph"
    driver: str = "bolt"
    dialect: str = "cypher"
    batch_size: int = 100
    # 指定节点的主键
    node_pro_key: dict = dict({
   
   'Ren':'zjhm','Aj':'ajbh','Che':'rowkey','Hh':'rowkey','Sj':'dhhm'})
    #指定需要导入的边
    specified_relation = ['ajgx','th','tfj','sysj','sycl']
    #指定需要导入的节点
    specified_node = ['Ren','Aj','Che','Sj','Hh']
    def __init__(self, driver, graph):
        """Initialize the connector with a Neo4j driver."""
        self._driver = driver
        self._schema = None
        self._graph = graph
        self._session = None

    @classmethod
    def from_uri_db(
            cls, host: str, port: int, user: str, pwd: str, db_name: str, db_type: str
    ) -> "GraphConnector":
        """Create a new TuGraphConnector from host, port, user, pwd, db_name."""
        try:
            from neo4j import GraphDatabase
            cls.db_type = db_type
            db_url = f"{
     
     cls.driver}://{
     
     host}:{
     
     str(port)}"
            driver = GraphDatabase.driver(db_url, auth=(user, pwd))
            driver.verify_connectivity()
            return cast(GraphConnector, cls(driver=driver, graph=db_name))

        except ImportError as err:
            raise ImportError(
                "neo4j package is not installed, please install it with "
                "`pip install neo4j`"
            ) from err

    def create_graph_new(self, graph_name: str) -> bool:
        """Create a new graph in the database if it doesn't already exist."""
        try:
            with self._driver.session() as session:
                graph_list = session.run("CALL dbms.graph.listGraphs()").data()
                exists = any(item["graph_name"] == graph_name for item in graph_list)
                if not exists:
                    session.run(
                        f"CALL dbms.graph.createGraph('{
     
     graph_name}', '', 2048)"
                    )
        except Exception as e:
            raise Exception(f"Failed to create graph '{
     
     graph_name}': {
     
     str(e)}") from e

        return not exists

    def create_vertex_labels(self, json_data):
        try:
            with self._driver.session(database=self._graph) as session:
                # graph_list = session.run(f"CALL db.createVertexLabelByJson({json_data})").data()
                session.run(
                    "CALL db.createVertexLabelByJson($json_data)",
                    json_data=json_data
                )
        except Exception as e:
            raise Exception(f"Failed to create vertex_labels ") from e

    # 批量更新节点，没有就新增，有就更新
    def batch_update_node(self, json_data):
        try:
            with self._driver.session(database=self._graph) as session:
                # graph_list = session.run(f"CALL db.createVertexLabelByJson({json_data})").data()
                session.upsertVertex(
                    "CALL db.upsertVertex($json_data)",
                    json_data=json_data
                )
        except Exception as e:
            raise Exception(f"Failed to create vertex_labels ") from e

    # 批量更新关系，没有就新增，有就更新
    def batch_update_edge(self, json_data):
        try:
            with self._driver.session(database=self._gra