1

我正在使用带有 cloudera-6.3.2 发行版的 hadoop 集群。我需要从 spark（Java 客户端）读取 hive ACID 表。所以原生火花不读蜂巢酸表。因此计划使用 Hive WareHouse 连接器。但低于例外。甚至也无法读取非酸性表。有什么想法吗？

20/03/27 21:26:46 INFO HiveWarehouseSessionImpl: Created a new HWC session: 9f46ffe3-c863-4fbf-82ef-9f730f0c0cfc
    20/03/27 21:26:47 INFO LlapBaseInputFormat: Handle ID 6439738b-a20a-46cc-9ee3-63214b573660: query=select * from test
    20/03/27 21:26:47 ERROR HiveConnection: Error opening session
    org.apache.thrift.TApplicationException: Required field 'client_protocol' is unset! Struct:TOpenSessionReq(client_protocol:null, configuration:{set:hiveconf:hive.server2.thrift.resultset.default.fetch.size=1000, use:database=default/})
        at org.apache.thrift.TApplicationException.read(TApplicationException.java:111)
        at org.apache.thrift.TServiceClient.receiveBase(TServiceClient.java:79)

Java 代码

HiveWarehouseSession hive = HiveWarehouseSession.session(spark).build();
 hive.executeQuery("select * from test").show();

这是我的 pom.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>fw_analytics</groupId>
    <artifactId>com.analytics</artifactId>
    <version>1.0-SNAPSHOT</version>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>8</source>
                    <target>8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>
    <packaging>jar</packaging>
    <dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.4.0-cdh6.3.2</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-hive_2.11</artifactId>
            <version>2.4.0-cdh6.3.2</version>
        </dependency>


        <dependency>
            <groupId>com.hortonworks.hive</groupId>
            <artifactId>hive-warehouse-connector_2.11</artifactId>
            <version>1.0.0.7.0.3.0-79</version>
        </dependency>
    </dependencies>

    <repositories>
        <repository>
            <releases>
                <enabled>true</enabled>
            </releases>
            <snapshots>
                <enabled>true</enabled>
            </snapshots>
            <id>hortonworks.extrepo</id>
            <name>Hortonworks HDP</name>
            <url>http://repo.hortonworks.com/content/repositories/releases</url>
        </repository>
        <repository>
            <releases>
                <enabled>true</enabled>
            </releases>
            <snapshots>
                <enabled>true</enabled>
            </snapshots>
            <id>Cloudera.extrepo</id>
            <name>Cloudera HDP</name>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
        </repository>
        <repository>
            <releases>
                <enabled>true</enabled>
            </releases>
            <snapshots>
                <enabled>true</enabled>
            </snapshots>
            <id>hortonworks.other</id>
            <name>Hortonworks Other Dependencies</name>
            <url>http://repo.hortonworks.com/content/groups/public</url>
        </repository>
    </repositories>

</project>
4

0 回答 0