流式计算 新年优惠活动

from pyflink.datastream import StreamExecutionEnvironment
from pyflink.table import TableEnvironment, DataTypes
from pyflink.table.udf import udf

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

# 定义数据源
source_ddl = """
    CREATE TABLE user_behavior (
        user_id BIGINT,
        item_id BIGINT,
        category_id INT,
        behavior STRING,
        ts TIMESTAMP(3)
    ) WITH (
        'connector' = 'kafka',
        'topic' = 'user_behavior',
        'properties.bootstrap.servers' = 'localhost:9092',
        'format' = 'json'
    )
"""
t_env.execute_sql(source_ddl)

# 定义UDF
@udf(input_types=[DataTypes.STRING()], result_type=DataTypes.INT())
def behavior_to_int(behavior):
    return 1 if behavior == 'click' else 0

# 注册UDF
t_env.register_function("behavior_to_int", behavior_to_int)

# 数据处理逻辑
result_table = t_env.sql_query("""
    SELECT user_id, item_id, behavior_to_int(behavior) as behavior_int
    FROM user_behavior
""")

# 输出结果
sink_ddl = """
    CREATE TABLE result (
        user_id BIGINT,
        item_id BIGINT,
        behavior_int INT
    ) WITH (
        'connector' = 'print'
    )
"""
t_env.execute_sql(sink_ddl)
result_table.execute_insert("result").wait()