flink scala mysql_Flink 读取 MySQL 示例

本文展示了如何使用 Flink Scala API 从 MySQL 数据库读取数据。提供了三种不同的方法创建 JDBC 输入格式,查询 MySQL 数据并打印输出,最后执行 Flink 作业。
摘要由CSDN通过智能技术生成

package org.onepiece.bigdata.windows.JDBCimportorg.apache.flink.api.common.typeinfo.{BasicTypeInfo, TypeInformation}importorg.apache.flink.api.java.io.jdbc.{JDBCAppendTableSink, JDBCInputFormat, JDBCOutputFormat}importorg.apache.flink.table.api.scala.BatchTableEnvironmentimportorg.apache.flink.table.api.{DataTypes, EnvironmentSettings, Types}importorg.apache.flink.types.Rowimportorg.apache.flink.api.java.typeutils.RowTypeInfoimportorg.apache.flink.streaming.api.scala.StreamExecutionEnvironmentimportorg.apache.flink.table.api.scala.StreamTableEnvironmentimportorg.apache.flink.table.api.Table

object mysql_test {importorg.apache.flink.api.scala.extensions._importorg.apache.flink.api.scala._

protected val host_name= "localhost"protected val port= 3306protected val db_name= "vn09jj5"protected val url= s"jdbc:mysql://${host_name}:${port}/${db_name}?useSSL=false&serverTimezone=UTC"val url_flink= "jdbc:mysql://localhost:3306/flink_db?useSSL=false&serverTimezone=UTC"protected val driver= "com.mysql.cj.jdbc.Driver"protected val user= "root"protected val password= "sa123ADMIN"

def getBatchExecutionEnvironment(): ExecutionEnvironment ={

val benv=ExecutionEnvironment.getExecutionEnvironmentreturnbenv

}def getStreamExecutionEnvironment(): StreamExecutionEnvironment ={

val senv=StreamExecutionEnvironment.getExecutionEnvironmentreturnsenv

}def getEnvironmentSettings(): EnvironmentSettings ={

val setting=EnvironmentSettings.newInstance()

.useBlinkPlanner()

.inStreamingMode()

.build()returnsetting

}def mysql_read_1(): Unit ={

val benv=ExecutionEnvironment.getExecutionEnvironment//读取MySQL

val dataSource=benv.createInput(

JDBCInputFormat.buildJDBCInputFormat()

.setDBUrl(url)

.setDrivername(driver)

.setUsername(user)

.setPassword(password)

.setQuery("select phone_Nbr,channel from cte_phone_channel order by phone_Nbr")

.setRowTypeInfo(new RowTypeInfo(

BasicTypeInfo.STRING_TYPE_INFO,//phone_Nbr

BasicTypeInfo.STRING_TYPE_INFO//channel

))

.finish()

)

dataSource.print()

println(dataSource.count())

benv.execute("mysql-test")

}def mysql_read_2(): Unit ={

val benv=ExecutionEnvironment.getExecutionEnvironment

val query_table=

"""|select a.phone_Nbr,a.channel,b.isDelete,b.remart

|from cte_phone_channel as a

|inner join order_phone as b on b.phone_Nbr=a.phone_Nbr and b.isDelete=1""".stripMargin//读取MySQL

val dataSource=benv.createInput(

JDBCInputFormat.buildJDBCInputFormat()

.setDBUrl(url)

.setDrivername(driver)

.setUsername(user)

.setPassword(password)

.setQuery(query_table)

.setRowTypeInfo(new RowTypeInfo(

BasicTypeInfo.STRING_TYPE_INFO,//phone_Nbr

BasicTypeInfo.STRING_TYPE_INFO,//channel

BasicTypeInfo.INT_TYPE_INFO,//isDelete

BasicTypeInfo.STRING_TYPE_INFO//remart

))

.finish()

)

dataSource.print()

println(dataSource.count())

benv.execute("mysql-test")

}def mysql_read_3(): Unit ={

val benv=ExecutionEnvironment.getExecutionEnvironment

val query= "select phone_Nbr,channel from cte_phone_channel order by phone_Nbr"val fields= Array[String]("phone_Nbr", "channel")

val types=Array[TypeInformation[_]](Types.STRING, Types.STRING)

val typeInfo=new RowTypeInfo(types, fields)//读取MySQL

val dataSource=benv.createInput(

JDBCInputFormat.buildJDBCInputFormat()

.setDBUrl(url)

.setDrivername(driver)

.setUsername(user)

.setPassword(password)

.setQuery(query)

.setRowTypeInfo(typeInfo)

.finish()

)

dataSource.print()

println(dataSource.count())

benv.execute("mysql-test")

}

}

以下是一个使用Java和Apache Flink连接MySQL读取binlog的代码,并且使用了Maven进行依赖管理。请注意,这里仅提供代码示例,具体的数据库连接信息和binlog配置需要根据实际情况进行修改。 pom.xml文件内容如下: ```xml <dependencies> <dependency> <groupId>org.apache.flink</groupId> <artifactId>flink-core</artifactId> <version>${flink.version}</version> </dependency> <dependency> <groupId>org.apache.flink</groupId> <artifactId>flink-streaming-java_${scala.binary.version}</artifactId> <version>${flink.version}</version> </dependency> <dependency> <groupId>org.apache.flink</groupId> <artifactId>flink-connector-jdbc_${scala.binary.version}</artifactId> <version>${flink.version}</version> </dependency> <dependency> <groupId>mysql</groupId> <artifactId>mysql-connector-java</artifactId> <version>${mysql.version}</version> </dependency> <dependency> <groupId>org.apache.flink</groupId> <artifactId>flink-connector-kafka_${scala.binary.version}</artifactId> <version>${flink.version}</version> </dependency> </dependencies> ``` Java代码实现如下: ```java import org.apache.flink.api.common.functions.MapFunction; import org.apache.flink.api.common.serialization.SimpleStringSchema; import org.apache.flink.streaming.api.datastream.DataStream; import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer; import org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer; import org.apache.flink.streaming.connectors.kafka.KafkaSerializationSchema; import org.apache.flink.streaming.connectors.kafka.KafkaSink; import org.apache.flink.streaming.connectors.kafka.KafkaTopicPartition; import org.apache.flink.streaming.connectors.kafka.internals.KeyedSerializationSchemaWrapper; import org.apache.flink.streaming.connectors.kafka.internals.KafkaTopicPartitionState; import org.apache.flink.streaming.connectors.kafka.internals.KafkaTopicPartitionStateSentinel; import org.apache.flink.streaming.connectors.kafka.internals.LegacyFetcher; import org.apache.flink.streaming.connectors.kafka.internals.LegacyFetcherThread; import org.apache.flink.streaming.connectors.kafka.internals.LegacyFlinkKafkaConsumer; import org.apache.flink.streaming.connectors.kafka.internals.LegacyFlinkKafkaConsumerBase; import org.apache.flink.streaming.connectors.kafka.internals.metrics.KafkaConsumerMetricConstants; import org.apache.flink.streaming.connectors.kafka.internals.metrics.KafkaConsumerMetricWrapper; import org.apache.kafka.clients.consumer.ConsumerRecord; import org.apache.kafka.clients.producer.ProducerConfig; import org.apache.kafka.clients.producer.ProducerRecord; import org.apache.kafka.common.TopicPartition; import org.apache.kafka.common.serialization.StringSerializer; import java.util.Properties; public class FlinkKafkaConnector { public static void main(String[] args) throws Exception { final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment(); //设置kafka相关参数 Properties properties = new Properties(); properties.setProperty("bootstrap.servers", "localhost:9092"); properties.setProperty("group.id", "test"); //创建KafkaSource FlinkKafkaConsumer<String> kafkaConsumer = new FlinkKafkaConsumer<>("test", new SimpleStringSchema(), properties); //将KafkaSource添加到Flink环境中 DataStream<String> stream = env.addSource(kafkaConsumer); //将数据转换成大写字母 DataStream<String> upperStream = stream.map(new MapFunction<String, String>() { @Override public String map(String s) throws Exception { return s.toUpperCase(); } }); //将数据写回到Kafka Properties producerProperties = new Properties(); producerProperties.setProperty(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, "localhost:9092"); FlinkKafkaProducer<String> kafkaProducer = new FlinkKafkaProducer<>("test", new KeyedSerializationSchemaWrapper<>(new SimpleStringSchema()), producerProperties, FlinkKafkaProducer.Semantic.EXACTLY_ONCE); upperStream.addSink(kafkaProducer); //执行任务 env.execute("Flink Kafka Connector Example"); } } ``` 需要注意的是,这里使用了Flink Kafka Connector,因此需要在pom.xml文件中加入相应的依赖。此外,还需要根据实际情况修改Kafka和MySQL的连接信息。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值