【Flink-Kafka-To-Kafka】使用 Flink 实现 Kafka 数据写入 Kafka
需求描述：
1、数据从 Kafka 写入 Kafka。
2、相关配置存放于 Mysql 中，通过 Mysql 进行动态读取。
3、此案例中的 Kafka 是进行了 Kerberos 安全认证的，如果不需要自行修改。
4、Kafka 数据为 Json 格式，通过 FlatMap 扁平化处理后完成写入。
5、读取时使用自定义 Source，写入时使用自定义 Sink。
6、本地测试时可以编辑 resources.flink_backup_local.yml 通过 ConfigTools.initConf 方法获取配置。
1）导入依赖
这里的依赖比较冗余，大家可以根据各自需求做删除或保留。
xml
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>example.cn.test</groupId>
<artifactId>kafkaetl2kafka</artifactId>
<version>1.0.0</version>
<properties>
<hbase.version>2.3.3</hbase.version>
<hadoop.version>3.1.1</hadoop.version>
<spark.version>3.0.2</spark.version>
<scala.version>2.12.10</scala.version>
<maven.compiler.source>8</maven.compiler.source>
<maven.compiler.target>8</maven.compiler.target>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<flink.version>1.14.0</flink.version>
<scala.binary.version>2.12</scala.binary.version>
<target.java.version>1.8</target.java.version>
<maven.compiler.source>${target.java.version}</maven.compiler.source>
<maven.compiler.target>${target.java.version}</maven.compiler.target>
<log4j.version>2.17.2</log4j.version>
<hadoop.version>3.1.2</hadoop.version>
<hive.version>3.1.2</hive.version>
<drools.version>7.18.0.Final</drools.version>
<cos_api>5.2.4</cos_api>
</properties>
<dependencies>
<!-- 基础依赖 开始-->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-java</artifactId>
<version>${flink.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-clients_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
<scope>provided</scope>
</dependency>
<!-- 基础依赖 结束-->
<!-- TABLE 开始-->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-table-api-java-bridge_${scala.binary.version}</artifactId>
<version>1.14.0</version>
<scope>provided</scope>
</dependency>
<!-- 使用 hive sql时注销，其他时候可以放开 -->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-table-planner_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-scala_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-table-common</artifactId>
<version>${flink.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-cep_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<!-- TABLE 结束-->
<!-- sql 开始-->
<!-- sql解析 开始 -->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-json</artifactId>
<version>${flink.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-csv</artifactId>
<version>${flink.version}</version>
<scope>provided</scope>
</dependency>
<!-- 检查点 -->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-state-processor-api_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>commons-lang</groupId>
<artifactId>commons-lang</artifactId>
<version>2.5</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-runtime-web_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
<scope>provided</scope>
</dependency>
<!-- 本地监控任务 结束 -->
<!-- DataStream 开始 -->
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-slf4j-impl</artifactId>
<version>${log4j.version}</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-api</artifactId>
<version>${log4j.version}</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-core</artifactId>
<version>${log4j.version}</version>
<scope>runtime</scope>
</dependency>
<!-- hdfs -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>3.3.1</version>
</dependency>
<!-- 重点，容易被忽略的jar -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-auth</artifactId>
<version>${hadoop.version}</version>
</dependency>
<!-- rocksdb_2 -->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-statebackend-rocksdb_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.projectlombok</groupId>
<artifactId>lombok</artifactId>
<version>1.16.18</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>gaei.cn.x5l</groupId>
<artifactId>acp-decode</artifactId>
<version>1.0.0</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-sql-connector-kafka_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.jyaml</groupId>
<artifactId>jyaml</artifactId>
<version>1.3</version>
</dependency>
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.44</version>
</dependency>
<dependency>
<groupId>com.bazaarvoice.jolt</groupId>
<artifactId>jolt-core</artifactId>
<version>0.1.1</version>
</dependency>
<dependency>
<groupId>com.bazaarvoice.jolt</groupId>
<artifactId>json-utils</artifactId>
<version>0.1.1</version>
</dependency>
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.1.23</version>
</dependency>
<dependency>
<groupId>redis.clients</groupId>
<artifactId>jedis</artifactId>
<version>2.9.0</version>
</dependency>
<dependency>
<groupId>org.drools</groupId>
<artifactId>drools-core</artifactId>
<version>${drools.version}</version>
</dependency>
<dependency>
<groupId>org.drools</groupId>
<artifactId>drools-compiler</artifactId>
<version>${drools.version}</version>
</dependency>
<dependency>
<groupId>org.kie</groupId>
<artifactId>kie-api</artifactId>
<version>${drools.version}</version>
</dependency>
<dependency>
<groupId>org.drools</groupId>
<artifactId>drools-templates</artifactId>
<version>${drools.version}</version>
</dependency>
<dependency>
<groupId>org.kie</groupId>
<artifactId>kie-internal</artifactId>
<version>${drools.version}</version>
</dependency>
<dependency>
<groupId>org.drools</groupId>
<artifactId>drools-decisiontables</artifactId>
<version>${drools.version}</version>
</dependency>
<dependency>
<groupId>cn.hutool</groupId>
<artifactId>hutool-all</artifactId>
<version>5.8.10</version>
</dependency>
<dependency>
<groupId>com.qcloud</groupId>
<artifactId>cos_api</artifactId>
<version>${cos_api}</version>
<exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</exclusion>
</exclusions>
</dependency>
</dependencies>
<build>
<plugins>
<!-- Java Compiler -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.1</version>
<configuration>
<source>${target.java.version}</source>
<target>${target.java.version}</target>
</configuration>
</plugin>
<!-- We use the maven-shade plugin to create a fat jar that contains all necessary dependencies. -->
<!-- Change the value of <mainClass>...</mainClass> if your program entry point changes. -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>3.0.0</version>
<executions>
<!-- Run shade goal on package phase -->
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<artifactSet>
<excludes>
<exclude>org.apache.flink:force-shading</exclude>
<exclude>com.google.code.findbugs:jsr305</exclude>
<exclude>org.slf4j:*</exclude>
<exclude>org.apache.logging.log4j:*</exclude>
<exclude>org.apache.flink:flink-runtime-web_2.11</exclude>
</excludes>
</artifactSet>
<filters>
<filter>
<!-- Do not copy the signatures in the META-INF folder.
Otherwise, this might cause SecurityExceptions when using the JAR. -->
<artifact>*:*</artifact>
<excludes>
<exclude>META-INF/*.SF</exclude>
<exclude>META-INF/*.DSA</exclude>
<exclude>META-INF/*.RSA</exclude>
</excludes>
</filter>
</filters>
<transformers>
<transformer
implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
<mainClass>com.owp.flink.kafka.KafkaSourceDemo</mainClass>
</transformer>
<!-- flink sql 需要 -->
<!-- The service transformer is needed to merge META-INF/services files -->
<transformer
implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer"/>
<!-- ... -->
</transformers>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
<pluginManagement>
<plugins>
<!-- This improves the out-of-the-box experience in Eclipse by resolving some warnings. -->
<plugin>
<groupId>org.eclipse.m2e</groupId>
<artifactId>lifecycle-mapping</artifactId>
<version>1.0.0</version>
<configuration>
<lifecycleMappingMetadata>
<pluginExecutions>
<pluginExecution>
<pluginExecutionFilter>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<versionRange>[3.0.0,)</versionRange>
<goals>
<goal>shade</goal>
</goals>
</pluginExecutionFilter>
<action>
<ignore/>
</action>
</pluginExecution>
<pluginExecution>
<pluginExecutionFilter>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<versionRange>[3.1,)</versionRange>
<goals>
<goal>testCompile</goal>
<goal>compile</goal>
</goals>
</pluginExecutionFilter>
<action>
<ignore/>
</action>
</pluginExecution>
</pluginExecutions>
</lifecycleMappingMetadata>
</configuration>
</plugin>
</plugins>
</pluginManagement>
</build>
</project>2）代码实现
2.1.resources
2.1.1.appconfig.yml
yml
mysql.url: "jdbc:mysql://1.1.1.1:3306/test?useSSL=false"
mysql.username: "test"
mysql.password: "123456"
mysql.driver: "com.mysql.jdbc.Driver"2.1.2.log4j.properties
shell
log4j.rootLogger=info, stdout
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%-4r [%t] %-5p %c %x - %m%n2.1.3.log4j2.xml
shell
<?xml version="1.0" encoding="UTF-8"?>
<configuration monitorInterval="5">
<Properties>
<property name="LOG_PATTERN" value="%date{HH:mm:ss.SSS} [%thread] %-5level %logger{36} - %msg%n" />
<property name="LOG_LEVEL" value="ERROR" />
</Properties>
<appenders>
<console name="console" target="SYSTEM_OUT">
<PatternLayout pattern="${LOG_PATTERN}"/>
<ThresholdFilter level="${LOG_LEVEL}" onMatch="ACCEPT" onMismatch="DENY"/>
</console>
<File name="log" fileName="tmp/log/job.log" append="false">
<PatternLayout pattern="%d{HH:mm:ss.SSS} %-5level %class{36} %L %M - %msg%xEx%n"/>
</File>
</appenders>
<loggers>
<root level="${LOG_LEVEL}">
<appender-ref ref="console"/>
<appender-ref ref="log"/>
</root>
</loggers>
</configuration>2.1.4.flink_backup_local.yml
yml
business:
datasource: 'TEST'
refreshdelay: 60000
refreshperiod: 60000
hdfs:
checkPointPath: 'hdfs://nameserver/user/flink/checkpoints'
checkpointTimeout: 600000
checkpointing: 60000
maxConcurrentCheckpoints: 1
minPauseBetweenCheckpoints: 10000
restartInterval: 120
restartStrategy: 3
kafka-consumer:
prop:
auto.offset.reset: 'earliest'
bootstrap.servers: 'kfk01:9092,kfk02:9092,kfk03:9092,kfk04:9092,kfk05:9092,kfk06:9092'
enable.auto.commit: 'false'
group.id: 'kafkaetl2kafka_test'
fetch.max.bytes: '10485760'
max.partition.fetch.bytes: '5242880'
max.poll.interval.ms: '2000000'
max.poll.records: '20000'
receive.buffer.bytes: '10485760'
send.buffer.bytes: '10485760'
session.timeout.ms: '18000000'
isKerberized: '1'
krb5Conf: '/opt/conf/krb5.conf'
security_protocol: 'SASL_PLAINTEXT'
useTicketCache: 'false'
serviceName: 'kafka'
keytab: '/opt/conf/test.keytab'
principal: 'test@TEST.TEST.COM'
topics: 'test'
kafka-producer:
kafkaProducersPoolSize: 5
defaultTopic: 'test'
prop:
acks: 'all'
bootstrap.servers: 'kfk01:9092,kfk02:9092,kfk03:9092,kfk04:9092,kfk05:9092,kfk06:9092'
compression.type: 'lz4'
retries: '40'
retry.backoff.ms: '5000'
batch.size: '262144'
buffer.memory: '536870912'
max.request.size: '2148576'
request.timeout.ms: '30000000'
send.buffer.bytes: '10485760'
receive.buffer.bytes: '10485760'
linger.ms: '10'
transaction.timeout.ms: '36000000'
isKerberized: '1'
krb5Conf: '/opt/conf/krb5.conf'
security_protocol: 'SASL_PLAINTEXT'
useTicketCache: 'false'
serviceName: 'kafka'
keytab: '/opt/conf/test.keytab'
principal: 'test@TEST.TEST.COM'
mysql:
password: '123456'
url: 'jdbc:mysql://1.1.1.1:3306/test'
username: 'test'
processParallelism: 48
ismap: 'false'
iskeyby: 'true'
isprint: 'false'
flatMapParallelism: '240'
sinkParallelism: '240'
sourceParallelism: '240'
redis:
block-when-exhausted: 'false'
database: 0
host: '1.1.1.1'
password: '123456'
port: 8250
timeout: 60000002.2.utils
2.2.1.DBConn
java
import java.sql.*;
public class DBConn {
private static final String driver = "com.mysql.jdbc.Driver"; //mysql驱动
private static Connection conn = null;
private static PreparedStatement ps = null;
private static ResultSet rs = null;
private static final CallableStatement cs = null;
/**
* 连接数据库
* @return
*/
public static Connection conn(String url,String username,String password) {
Connection conn = null;
try {
Class.forName(driver); //加载数据库驱动
try {
conn = DriverManager.getConnection(url, username, password); //连接数据库
} catch (SQLException e) {
e.printStackTrace();
}
} catch (ClassNotFoundException e) {
e.printStackTrace();
}
return conn;
}
/**
* 关闭数据库链接
* @return
*/
public static void close() {
if(conn != null) {
try {
conn.close(); //关闭数据库链接
} catch (SQLException e) {
e.printStackTrace();
}
}
}
}2.2.2.CommonUtils
java
@Slf4j
public class CommonUtils {
public static StreamExecutionEnvironment setCheckpoint(StreamExecutionEnvironment env) throws IOException {
// ConfigTools.initConf("local");
Map hdfsMap = (Map) ConfigTools.mapConf.get("hdfs");
env.enableCheckpointing(((Integer) hdfsMap.get("checkpointing")).longValue(), CheckpointingMode.EXACTLY_ONCE);//这里会造成offset提交的延迟
env.getCheckpointConfig().setMinPauseBetweenCheckpoints(((Integer) hdfsMap.get("minPauseBetweenCheckpoints")).longValue());
env.getCheckpointConfig().setCheckpointTimeout(((Integer) hdfsMap.get("checkpointTimeout")).longValue());
env.getCheckpointConfig().setMaxConcurrentCheckpoints((Integer) hdfsMap.get("maxConcurrentCheckpoints"));
env.getCheckpointConfig().enableExternalizedCheckpoints(CheckpointConfig.ExternalizedCheckpointCleanup.RETAIN_ON_CANCELLATION);
env.setRestartStrategy(RestartStrategies.fixedDelayRestart(
(Integer) hdfsMap.get("restartStrategy"), // 尝试重启的次数，不宜过小，分布式任务很容易出问题（正常情况），建议3-5次
Time.of(((Integer) hdfsMap.get("restartInterval")).longValue(), TimeUnit.SECONDS) // 延时
));
//设置可容忍的检查点失败数，默认值为0表示不允许容忍任何检查点失败
env.getCheckpointConfig().setTolerableCheckpointFailureNumber(2);
//设置状态后端存储方式
env.setStateBackend(new RocksDBStateBackend((String) hdfsMap.get("checkPointPath"), true));
// env.setStateBackend(new FsStateBackend((String) hdfsMap.get("checkPointPath"), true));
// env.setStateBackend(new HashMapStateBackend(());
return env;
}
public static FlinkKafkaConsumer<ConsumerRecord<String, String>> getKafkaConsumer(Map<String, Object> kafkaConf) throws IOException {
String[] topics = ((String) kafkaConf.get("topics")).split(",");
log.info("监听的topic: {}", topics);
Properties properties = new Properties();
Map<String, String> kafkaProp = (Map<String, String>) kafkaConf.get("prop");
for (String key : kafkaProp.keySet()) {
properties.setProperty(key, kafkaProp.get(key).toString());
}
if (!StringUtils.isBlank((String) kafkaProp.get("isKerberized")) && "1".equals(kafkaProp.get("isKerberized"))) {
System.setProperty("java.security.krb5.conf", kafkaProp.get("krb5Conf"));
properties.put("security.protocol", kafkaProp.get("security_protocol"));
properties.put("sasl.jaas.config", "com.sun.security.auth.module.Krb5LoginModule required "
+ "useTicketCache=" + kafkaProp.get("useTicketCache") + " "
+ "serviceName=\"" + kafkaProp.get("serviceName") + "\" "
+ "useKeyTab=true "
+ "keyTab=\"" + kafkaProp.get("keytab").toString() + "\" "
+ "principal=\"" + kafkaProp.get("principal").toString() + "\";");
}
properties.put("key.serializer", "org.apache.flink.kafka.shaded.org.apache.kafka.common.serialization.ByteArrayDeserializer");
properties.put("value.serializer", "org.apache.flink.kafka.shaded.org.apache.kafka.common.serialization.ByteArrayDeserializer");
FlinkKafkaConsumer<ConsumerRecord<String, String>> consumerRecordFlinkKafkaConsumer = new FlinkKafkaConsumer<ConsumerRecord<String, String>>(Arrays.asList(topics), new KafkaDeserializationSchema<ConsumerRecord<String, String>>() {
@Override
public TypeInformation<ConsumerRecord<String, String>> getProducedType() {
return TypeInformation.of(new TypeHint<ConsumerRecord<String, String>>() {
});
}
@Override
public boolean isEndOfStream(ConsumerRecord<String, String> stringStringConsumerRecord) {
return false;
}
@Override
public ConsumerRecord<String, String> deserialize(ConsumerRecord<byte[], byte[]> record) throws Exception {
return new ConsumerRecord<String, String>(
record.topic(),
record.partition(),
record.offset(),
record.timestamp(),
record.timestampType(),
record.checksum(),
record.serializedKeySize(),
record.serializedValueSize(),
new String(record.key() == null ? "".getBytes(StandardCharsets.UTF_8) : record.key(), StandardCharsets.UTF_8),
new String(record.value() == null ? "{}".getBytes(StandardCharsets.UTF_8) : record.value(), StandardCharsets.UTF_8));
}
}, properties);
return consumerRecordFlinkKafkaConsumer;
}
public static FlinkKafkaProducer getKafkaSink(Map conf) {
Map kafkaProducer = (Map) conf.get("kafka-producer");
Integer kafkaProducersPoolSize = (Integer) kafkaProducer.get("kafkaProducersPoolSize") == null ? 5 : (Integer) kafkaProducer.get("kafkaProducersPoolSize");
/* conf/ 为配置文件相对yarn cache的相对路径，这里源kafka和目的kafka用的是同一个krb5.conf，如果源kafka和目的kafka使用不同的KDC，
需要分别设置对应各自KDC的krb5.conf
*/
// System.setProperty("java.security.krb5.conf", "conf/krb5.conf");
String defaultTopic = (String) kafkaProducer.get("defaultTopic");
Map<String, String> kafkaProp = (Map<String, String>) kafkaProducer.get("prop");
Properties properties = new Properties();
for (Map.Entry<String, String> entry : kafkaProp.entrySet()) {
String mapKey = entry.getKey();
String mapValue = entry.getValue();
properties.put(mapKey, mapValue);
}
if (!StringUtils.isBlank((String) kafkaProp.get("isKerberized")) && "1".equals(kafkaProp.get("isKerberized"))) {
System.setProperty("java.security.krb5.conf", kafkaProp.get("krb5Conf"));
properties.put("security.protocol", kafkaProp.get("security_protocol"));
properties.put("sasl.jaas.config", "com.sun.security.auth.module.Krb5LoginModule required "
+ "useTicketCache=" + kafkaProp.get("useTicketCache") + " "
+ "serviceName=\"" + kafkaProp.get("serviceName") + "\" "
+ "useKeyTab=true "
+ "keyTab=\"" + kafkaProp.get("keytab").toString() + "\" "
+ "principal=\"" + kafkaProp.get("principal").toString() + "\";");
}
FlinkKafkaProducer<ConsumerRecord<String, String>> myProducer = new FlinkKafkaProducer<ConsumerRecord<String, String>>(
defaultTopic,
new ProductDeSerializationSchema(defaultTopic),
properties,
FlinkKafkaProducer.Semantic.AT_LEAST_ONCE, kafkaProducersPoolSize);
return myProducer;
}
}2.3.conf
2.3.1.ConfigTools
java
@Slf4j
public class ConfigTools {
public static Map<String, Object> mapConf;
/**
* 获取对应的配置文件
*
* @param option
*/
public static void initConf(String option) {
String confFile = "/flink_backup_" + option + ".yml";
try {
InputStream dumpFile = ConfigTools.class.getResourceAsStream(confFile);
mapConf = Yaml.loadType(dumpFile, HashMap.class);
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* 获取对应的配置文件
*
* @param option
*/
public static void initMySqlConf(String option, Class clazz) {
String className = clazz.getName();
String confFile = "/appconfig.yml";
Map<String, String> mysqlConf;
try {
InputStream dumpFile = ConfigTools.class.getResourceAsStream(confFile);
mysqlConf = Yaml.loadType(dumpFile, HashMap.class);
String username = mysqlConf.get("mysql.username");
String password = mysqlConf.get("mysql.password");
String url = mysqlConf.get("mysql.url");
Connection conn = DBConn.conn(url, username, password);
Map<String, Object> config = getConfig(conn, className, option);
if (config == null || config.size() == 0) {
log.error("获取配置文件失败");
return;
}
mapConf = config;
} catch (Exception e) {
e.printStackTrace();
}
}
private static Map<String, Object> getConfig(Connection conn, String className, String option) throws SQLException {
PreparedStatement preparedStatement = null;
try {
String sql = "select config_context from app_config where app_name = '%s' and config_name = '%s'";
preparedStatement = conn.prepareStatement(String.format(sql, className, option));
ResultSet rs = preparedStatement.executeQuery();
Map<String, String> map = new LinkedHashMap<>();
String config_context = "";
while (rs.next()) {
config_context = rs.getString("config_context");
}
System.out.println("配置信息config_context："+config_context);
// if(StringUtils.isNotBlank(config_context)){
// System.out.println(JSONObject.toJSONString(JSONObject.parseObject(config_context), SerializerFeature.PrettyFormat));
// }
Map<String, Object> mysqlConfMap = JSON.parseObject(config_context, Map.class);
return mysqlConfMap;
}finally {
if (preparedStatement != null) {
preparedStatement.close();
}
if (conn != null) {
conn.close();
}
}
}
public static void main(String[] args) {
// initMySqlConf("local", TboxPeriodBackoutA3K.class);
initConf("local");
String s = JSON.toJSONString(mapConf);
System.out.println(s);
}
}2.4.serialier
2.4.1.ProductDeSerializationSchema
java
/**
* flink生产者序列化类
*/
public class ProductDeSerializationSchema implements KafkaSerializationSchema<ConsumerRecord<String, String>> {
private String topic;
// public Map conf;
// public Map<String, String> map = new HashMap<>();
public ProductDeSerializationSchema(String topic) {
this.topic = topic;
}
// @Override
// public void open(SerializationSchema.InitializationContext context) throws Exception {
// Map kafkaProducer = (Map) conf.get("kafka-producer");
// Map kafkaConsumer = (Map) conf.get("kafka-consumer");
// List<String> sinkTopics = Arrays.asList(((String) kafkaProducer.get("outPutTopic")).split(","));
// List<String> sourceTopics = Arrays.asList(((String) kafkaConsumer.get("topics")).split(","));
// for (int i = 0; i < sourceTopics.size(); i++) {
// map.put(sourceTopics.get(i), sinkTopics.get(i));
// }
// }
@Override
public ProducerRecord<byte[], byte[]> serialize(ConsumerRecord<String, String> record, @Nullable Long aLong) {
return new ProducerRecord<byte[], byte[]>(topic, record.key().getBytes(), record.value().getBytes());
}
}2.5.kafka2kafka
2.5.1.Kafka2Kafka
java
public class Kafka2Kafka {
public static Logger logger = Logger.getLogger(Kafka2Kafka.class);
public static void main(String[] args) throws Exception {
ConfigTools.initMySqlConf(args[0], Kafka2Kafka.class);
// ConfigTools.initConf("local");
//获取环境
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment().disableOperatorChaining();
//配置checkpoint
CommonUtils.setCheckpoint(env);
FlinkKafkaConsumer<ConsumerRecord<String, String>> myConsumer = CommonUtils.getKafkaConsumer();
//获取mysql配置文件
Map<String, Object> mapConf = ConfigTools.mapConf;
DataStream<ConsumerRecord<String, String>> stream = env.addSource(myConsumer);
//sink
FlinkKafkaProducer kafkaSink = CommonUtils.getKafkaSink(mapConf);
stream.addSink(kafkaSink);
//执行
env.execute();
}
}