Flink 对接 Hudi 查询数据，java代码编写

1.pom.xml文件需要引入下面包

    <properties><flink.version>1.15.4</flink.version><hudi.version>0.13.1</hudi.version></properties><dependencies><dependency><groupId>org.apache.flink</groupId><artifactId>flink-streaming-java</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-table-api-java-bridge</artifactId><version>${flink.version}</version><scope>provided</scope></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-table-planner_2.12</artifactId><version>${flink.version}</version><scope>provided</scope></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-connector-files</artifactId><version>${flink.version}</version><scope>provided</scope></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-clients</artifactId><version>${flink.version}</version><scope>provided</scope></dependency><!-- hudi --><dependency><groupId>org.apache.hudi</groupId><artifactId>hudi-flink1.15-bundle</artifactId><version>${hudi.version}</version><scope>provided</scope></dependency><dependency><groupId>org.apache.hudi</groupId><artifactId>hudi-flink-client</artifactId><version>0.14.1</version></dependency></dependencies>

2.java代码如下

import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;
import org.apache.flink.types.Row;
import org.junit.Test;import java.util.List;public class HudiTest {@Testpublic void test01() throws Exception {StreamExecutionEnvironment streamEnv = StreamExecutionEnvironment.getExecutionEnvironment();StreamTableEnvironment  tableEnv = StreamTableEnvironment.create(streamEnv);tableEnv.executeSql("CREATE TABLE IF NOT EXISTS table_name (\n" +"    resume_id bigint,\n" +"    update_by STRING,\n" +"    gmt_modified Timestamp ,\n" +"    del_flag int, \n" +"    invite_operation_date STRING,\n" +"    induct_date date ,\n" +"    leave_date date ,\n" +"    PRIMARY KEY (resume_id) NOT ENFORCED\n" +") with (\n" +" 'connector' = 'hudi',\n" +" 'path' = 'hdfs://177.17.17.200:8088/user/hudi/resume_demo/hr_resume',\n" +" 'table.type' = 'MERGE_ON_READ'\n" +")");Table table = tableEnv.sqlQuery("select * from table_name");// 启动 Flink 作业DataStream<Row> dataStream = tableEnv.toDataStream(table);streamEnv.execute();List<Row> rows = dataStream.executeAndCollect(100);//收集100条数据for (Row row : rows) {StringBuilder rowString = new StringBuilder();for (int i = 0; i < row.getArity(); i++) {rowString.append(row.getField(i)).append("|");}System.out.println(rowString.toString());}}
}

3.说明

经过测试，这里的sql中，支持下面的一些sql
简单where条件
limit 10 offset 0
不支持
order by