Spark操作Hudi

pom文件如下

<?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>org.hj</groupId>
    <artifactId>hudi-test</artifactId>
    <version>1.0-SNAPSHOT</version>

    <name>hudi-test</name>
    <url>http://www.example.com</url>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <scala.version>2.11.8</scala.version>
        <scala.compat.version>2.11.8</scala.compat.version>
        <scala.binary.version>2.11</scala.binary.version>
        <spark.version>2.4.4</spark.version>
        <hoodie.version>0.5.3-SNAPSHOT</hoodie.version>
        <scalikejdbc.version>2.5.0</scalikejdbc.version>
        <hadoop.version>2.7.3</hadoop.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
            <exclusions>
                <exclusion>
                    <groupId>org.apache.hadoop</groupId>
                    <artifactId>hadoop-common</artifactId>
                </exclusion>
            </exclusions>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
            <scope>provided</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-10_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-avro_2.11</artifactId>
            <version>2.4.4</version>
        </dependency>

        <!--<dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-hive_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
            <scope>provided</scope>
        </dependency>-->

        <dependency>
            <groupId>org.apache.hudi</groupId>
            <artifactId>hudi-spark-bundle_2.11</artifactId>
            <version>0.5.3</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hudi</groupId>
            <artifactId>hudi-common</artifactId>
            <version>0.5.3</version>
        </dependency>

        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.29</version>
        </dependency>

        <dependency>
            <groupId>com.typesafe</groupId>
            <artifactId>config</artifactId>
            <version>1.3.1</version>
        </dependency>

        <dependency>
            <groupId>org.scalikejdbc</groupId>
            <artifactId>scalikejdbc_${scala.binary.version}</artifactId>
            <version>${scalikejdbc.version}</version>
        </dependency>

        <dependency>
            <groupId>org.scalikejdbc</groupId>
            <artifactId>scalikejdbc-core_${scala.binary.version}</artifactId>
            <version>${scalikejdbc.version}</version>
        </dependency>

        <dependency>
            <groupId>org.scalikejdbc</groupId>
            <artifactId>scalikejdbc-config_${scala.binary.version}</artifactId>
            <version>${scalikejdbc.version}</version>
        </dependency>

        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.47</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
            <exclusions>
                <exclusion>
                    <groupId>org.apache.httpcomponents</groupId>
                    <artifactId>httpclient</artifactId>
                </exclusion>
                <exclusion>
                    <artifactId>slf4j-log4j12</artifactId>
                    <groupId>org.slf4j</groupId>
                </exclusion>
                <exclusion>
                    <artifactId>slf4j-api</artifactId>
                    <groupId>org.slf4j</groupId>
                </exclusion>
            </exclusions>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>${hadoop.version}</version>
            <exclusions>
                <exclusion>
                    <artifactId>slf4j-log4j12</artifactId>
                    <groupId>org.slf4j</groupId>
                </exclusion>
                <exclusion>
                    <artifactId>slf4j-api</artifactId>
                    <groupId>org.slf4j</groupId>
                </exclusion>
                <exclusion>
                    <groupId>org.apache.httpcomponents</groupId>
                    <artifactId>httpclient</artifactId>
                </exclusion>
            </exclusions>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>${hadoop.version}</version>
            <exclusions>
                <exclusion>
                    <artifactId>slf4j-log4j12</artifactId>
                    <groupId>org.slf4j</groupId>
                </exclusion>
                <exclusion>
                    <artifactId>slf4j-api</artifactId>
                    <groupId>org.slf4j</groupId>
                </exclusion>
                <exclusion>
                    <groupId>xml-apis</groupId>
                    <artifactId>xml-apis</artifactId>
                </exclusion>
            </exclusions>
        </dependency>

        <dependency>
            <groupId>org.apache.parquet</groupId>
            <artifactId>parquet-avro</artifactId>
            <version>1.10.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-jdbc</artifactId>
            <version>2.3.1</version>
            <scope>provided</scope>
            <exclusions>
                <exclusion>
                    <groupId>javax.mail</groupId>
                    <artifactId>mail</artifactId>
                </exclusion>
                <exclusion>
                    <groupId>org.eclipse.jetty.aggregate</groupId>
                    <artifactId>*</artifactId>
                </exclusion>
            </exclusions>
        </dependency>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-exec</artifactId>
            <version>2.3.1</version>
            <scope>provided</scope>
            <exclusions>
                <exclusion>
                    <groupId>javax.mail</groupId>
                    <artifactId>mail</artifactId>
                </exclusion>
                <exclusion>
                    <groupId>org.eclipse.jetty.aggregate</groupId>
                    <artifactId>*</artifactId>
                </exclusion>
            </exclusions>
        </dependency>

        <dependency>
            <groupId>com.facebook.presto</groupId>
            <artifactId>presto-jdbc</artifactId>
            <version>0.217</version>
        </dependency>

    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>2.3.2</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>${project.build.sourceEncoding}</encoding>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.scala-tools</groupId>
                <artifactId>maven-scala-plugin</artifactId>
                <version>2.15.2</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

将core-site.xml、hdfs-site.xml、hive-site.xml、yarn-site.xml导入到resources目录下。

插入数据

package com.hudi

import org.apache.hudi.DataSourceWriteOptions
import org.apache.hudi.config.HoodieWriteConfig
import org.apache.spark.sql.{SaveMode, SparkSession}
import org.hj.hudi.Util

object HudiInsert {
    def main(args: Array[String]): Unit = {
        val spark = SparkSession.builder.appName("hudi insert").config("spark.serializer", "org.apache.spark.serializer.KryoSerializer").master("local[3]").getOrCreate()
        val insertData = Util.readFromTxtByLineToDf(spark,"E:\\Demo\\hudi-test-master\\src\\main\\resources\\test_insert_data.txt")
        insertData.write.format("org.apache.hudi")
            // 设置主键列名
            .option(DataSourceWriteOptions.RECORDKEY_FIELD_OPT_KEY, "rowkey")
            // 设置数据更新时间的列名
            .option(DataSourceWriteOptions.PRECOMBINE_FIELD_OPT_KEY, "lastupdatedttm")
            // 并行度参数设置
            .option("hoodie.insert.shuffle.parallelism", "2")
            .option("hoodie.upsert.shuffle.parallelism", "2")
            // 表名设置
            .option(HoodieWriteConfig.TABLE_NAME, "test")
            .mode(SaveMode.Overwrite)
            // 写入路径设置
            .save("/tmp/hudi")
    }

}

插入分区数据

package com.hudi

import org.apache.hudi.DataSourceWriteOptions
import org.apache.hudi.config.{HoodieIndexConfig, HoodieWriteConfig}
import org.apache.hudi.index.HoodieIndex
import org.apache.spark.sql.{SaveMode, SparkSession}
import org.hj.hudi.Util

object HudiInsertBy {
    def main(args: Array[String]): Unit = {
        val spark = SparkSession.builder.appName("hudi insert").config("spark.serializer", "org.apache.spark.serializer.KryoSerializer").master("local[*]").getOrCreate()
        // 读取文本文件转换为df
        val insertData = Util.readFromTxtByLineToDf(spark, "E:\\Demo\\hudi-test-master\\src\\main\\resources\\test_insert_data.txt")
        insertData.write.format("org.apache.hudi")
            // 设置主键列名
            .option(DataSourceWriteOptions.RECORDKEY_FIELD_OPT_KEY, "rowkey")
            // 设置数据更新时间的列名
            .option(DataSourceWriteOptions.PRECOMBINE_FIELD_OPT_KEY, "lastupdatedttm")
            // 设置分区列
            .option(DataSourceWriteOptions.PARTITIONPATH_FIELD_OPT_KEY, "dt")
            // 设置当分区变更时，当前数据的分区目录是否变更
            .option(HoodieIndexConfig.BLOOM_INDEX_UPDATE_PARTITION_PATH, "true")
            // 设置索引类型目前有HBASE,INMEMORY,BLOOM,GLOBAL_BLOOM 四种索引 为了保证分区变更后能找到必须设置全局GLOBAL_BLOOM
            .option(HoodieIndexConfig.INDEX_TYPE_PROP, HoodieIndex.IndexType.GLOBAL_BLOOM.name())
            // 并行度参数设置
            .option("hoodie.insert.shuffle.parallelism", "2")
            .option("hoodie.upsert.shuffle.parallelism", "2")
            .option(HoodieWriteConfig.TABLE_NAME, "test_partition")
            .mode(SaveMode.Overwrite)
            .save("/tmp/hudi")
    }
}

更新数据(存在数据修改，不存在数据新增)

package com.hudi

import org.apache.hudi.DataSourceWriteOptions
import org.apache.hudi.config.HoodieWriteConfig
import org.apache.spark.sql.{SaveMode, SparkSession}
import org.hj.hudi.Util

object HudiUpsert {
    def main(args: Array[String]): Unit = {
        val spark = SparkSession.builder.appName("hudi upsert").config("spark.serializer", "org.apache.spark.serializer.KryoSerializer").master("local[3]").getOrCreate()
        val upsertData = Util.readFromTxtByLineToDf(spark, "E:\\Demo\\hudi-test-master\\src\\main\\resources\\test_update_data.txt")

        upsertData.write.format("org.apache.hudi")
            // 设置主键列名
            .option(DataSourceWriteOptions.RECORDKEY_FIELD_OPT_KEY, "rowkey")
            // 设置数据更新时间的列名
            .option(DataSourceWriteOptions.PRECOMBINE_FIELD_OPT_KEY, "lastupdatedttm")
            // 表名称设置
            .option(HoodieWriteConfig.TABLE_NAME, "test")
            // 并行度参数设置
            .option("hoodie.insert.shuffle.parallelism", "2")
            .option("hoodie.upsert.shuffle.parallelism", "2")
            .mode(SaveMode.Append)
            // 写入路径设置
            .save("/tmp/hudi");
    }
}

更新分区数据

package com.hudi

import org.apache.hudi.DataSourceWriteOptions
import org.apache.hudi.config.{HoodieIndexConfig, HoodieWriteConfig}
import org.apache.hudi.index.HoodieIndex
import org.apache.spark.sql.{SaveMode, SparkSession}
import org.hj.hudi.Util

object HudiUpsertBy {
    def main(args: Array[String]): Unit = {
        val spark = SparkSession.builder.appName("upsert partition").config("spark.serializer", "org.apache.spark.serializer.KryoSerializer").master("local[3]").getOrCreate()
        val upsertData = Util.readFromTxtByLineToDf(spark, "E:\\Demo\\hudi-test-master\\src\\main\\resources\\test_partition_update_data.txt")

        upsertData.write.format("org.apache.hudi").option(DataSourceWriteOptions.RECORDKEY_FIELD_OPT_KEY, "rowkey")
            .option(DataSourceWriteOptions.PRECOMBINE_FIELD_OPT_KEY, "lastupdatedttm")
            // 分区列设置
            .option(DataSourceWriteOptions.PARTITIONPATH_FIELD_OPT_KEY, "dt")
            .option(HoodieWriteConfig.TABLE_NAME, "test_partition")
            .option(HoodieIndexConfig.INDEX_TYPE_PROP, HoodieIndex.IndexType.GLOBAL_BLOOM.name())
            .option("hoodie.insert.shuffle.parallelism", "2")
            .option("hoodie.upsert.shuffle.parallelism", "2")
            .mode(SaveMode.Append)
            .save("/tmp/hudi");
    }
}

删除数据(和更新数据一样，存在数据删除)

package com.hudi

import org.apache.hudi.DataSourceWriteOptions
import org.apache.hudi.config.HoodieWriteConfig
import org.apache.spark.sql.{SaveMode, SparkSession}
import org.hj.hudi.Util

object HudiDelte {
    def main(args: Array[String]): Unit = {
        val spark = SparkSession.builder.appName("delta insert").config("spark.serializer", "org.apache.spark.serializer.KryoSerializer").master("local[3]").getOrCreate()
        val deleteData = Util.readFromTxtByLineToDf(spark, "E:\\Demo\\hudi-test-master\\src\\main\\resources\\test_partition_delete_data.txt")
        deleteData.write.format("com.uber.hoodie")
            // 设置主键列名
            .option(DataSourceWriteOptions.RECORDKEY_FIELD_OPT_KEY, "rowkey")
            // 设置数据更新时间的列名
            .option(DataSourceWriteOptions.PRECOMBINE_FIELD_OPT_KEY, "lastupdatedttm")
            // 表名称设置
            .option(HoodieWriteConfig.TABLE_NAME, "test")
            // 硬删除配置
            .option(DataSourceWriteOptions.PAYLOAD_CLASS_OPT_KEY, "org.apache.hudi.EmptyHoodieRecordPayload")
    }
}

查询数据

package com.hudi

import org.apache.spark.sql.SparkSession

object HudiQuery {
    def main(args: Array[String]): Unit = {
        val basePath = "/tmp/hudi"
        val spark = SparkSession.builder.appName("query insert").config("spark.serializer", "org.apache.spark.serializer.KryoSerializer").master("local[3]").getOrCreate()
        val tripsSnapshotDF = spark.
            read.
            format("org.apache.hudi").
            load(basePath + "/*/*")

        tripsSnapshotDF.show()
    }

}