大数据实时交互体验

from pyflink.datastream import StreamExecutionEnvironment
from pyflink.table import StreamTableEnvironment, DataTypes
from pyflink.table.descriptors import Kafka, Schema

# 创建执行环境
env = StreamExecutionEnvironment.get_execution_environment()
t_env = StreamTableEnvironment.create(env)

# 配置Kafka连接
t_env.connect(Kafka()
              .version("universal")
              .topic("test_topic")
              .start_from_latest()
              .property("zookeeper.connect", "localhost:2181")
              .property("bootstrap.servers", "localhost:9092"))
    .with_format("json")
    .with_schema(Schema()
                 .field("id", DataTypes.INT())
                 .field("value", DataTypes.STRING()))
    .create_temporary_table("kafka_input")

# 读取数据并进行处理
table = t_env.from_path("kafka_input")
result = table.filter(table.value.like("%error%")).select("id, value")

# 输出结果到控制台
result.execute().print()