如何在DSE中使用Java API访问Hive

Question

I'm working on 5 node cluster with 2 cassandra,2 solr and 1 hadoop node on DSE 4.0.3 , I'm trying to connect Hive thru java api. Below is the program I'm trying to execute

import java.sql.SQLException;
import java.sql.Connection;
import java.sql.ResultSet;
import java.sql.Statement;
import java.sql.DriverManager;

public class HiveJdbcClient {
    private static String driverName = "org.apache.hadoop.hive.jdbc.HiveDriver";

 /**
 * @param args
 * @throws SQLException
  */
 public static void main(String[] args) throws SQLException {
    try {
      Class.forName(driverName);
    } catch (ClassNotFoundException e) {
    // TODO Auto-generated catch block
    e.printStackTrace();
    System.exit(1);
  }
  Connection con = DriverManager.getConnection("jdbc:hive://localhost:10000/default",  "", "");
  Statement stmt = con.createStatement();
  String tableName = "testHiveDriverTable";
  stmt.executeQuery("drop table " + tableName);
  ResultSet res = stmt.executeQuery("create table " + tableName + " (key int, value string)");
 // show tables
  String sql = "show tables '" + tableName + "'";
  System.out.println("Running: " + sql);
  res = stmt.executeQuery(sql);
  if (res.next()) {
    System.out.println(res.getString(1));
  }
  // describe table
  sql = "describe " + tableName;
  System.out.println("Running: " + sql);
  res = stmt.executeQuery(sql);
  while (res.next()) {
    System.out.println(res.getString(1) + "\t" + res.getString(2));
  }

  // load data into table
  // NOTE: filepath has to be local to the hive server
  // NOTE: /tmp/a.txt is a ctrl-A separated file with two fields per line
  String filepath = "/tmp/a.txt";
  sql = "load data local inpath '" + filepath + "' into table " + tableName;
  System.out.println("Running: " + sql);
  res = stmt.executeQuery(sql);

  // select * query
  sql = "select * from " + tableName;
  System.out.println("Running: " + sql);
  res = stmt.executeQuery(sql);
  while (res.next()) {
    System.out.println(String.valueOf(res.getInt(1)) + "\t" + res.getString(2));
  }

  // regular hive query
  sql = "select count(1) from " + tableName;
  System.out.println("Running: " + sql);
  res = stmt.executeQuery(sql);
  while (res.next()) {
    System.out.println(res.getString(1));
   }
  }
}

But I'm getting error when

Connection con = DriverManager.getConnection("jdbc:hive://localhost:10000/default", "", "");


Exception in thread "main" java.lang.NoSuchMethodError: org.apache.thrift.protocol.TProtocol.getScheme()Ljava/lang/Class;
at org.apache.hadoop.hive.service.ThriftHive$execute_args.write(ThriftHive.java:1076)
at org.apache.thrift.TServiceClient.sendBase(TServiceClient.java:63)
at org.apache.hadoop.hive.service.ThriftHive$Client.send_execute(ThriftHive.java:110)
at org.apache.hadoop.hive.service.ThriftHive$Client.execute(ThriftHive.java:102)
at org.apache.hadoop.hive.jdbc.HiveStatement.executeQuery(HiveStatement.java:192)
at org.apache.hadoop.hive.jdbc.HiveStatement.execute(HiveStatement.java:132)
at org.apache.hadoop.hive.jdbc.HiveConnection.configureConnection(HiveConnection.java:132)
at org.apache.hadoop.hive.jdbc.HiveConnection.<init>(HiveConnection.java:122)
at org.apache.hadoop.hive.jdbc.HiveDriver.connect(HiveDriver.java:106)
at java.sql.DriverManager.getConnection(Unknown Source)
at java.sql.DriverManager.getConnection(Unknown Source)
at example.create.HiveTable.main(HiveTable.java:22)

Note: I have started thrift server while running program $ dse hive --service hiveserver

And Also I'm getting when

Connection con = DriverManager.getConnection("jdbc:hive2://localhost:10000/default", "", "");

Exception in thread "main" java.sql.SQLException: Invalid URL: jdbc:hive2://54.243.203.229:10000/default
at org.apache.hadoop.hive.jdbc.HiveConnection.<init>(HiveConnection.java:86)
at org.apache.hadoop.hive.jdbc.HiveDriver.connect(HiveDriver.java:106)
at java.sql.DriverManager.getConnection(Unknown Source)
at java.sql.DriverManager.getConnection(Unknown Source)
at example.create.HiveTable.main(HiveTable.java:22)

Note: I have started thrift server while running program $ dse hive --service hiveserver2

Hite-site.xml is :

<configuration>
<!--Hive Execution Parameters -->
  <property>
          <name>hive.exec.mode.local.auto</name>
          <value>false</value>
          <description>Let hive determine whether to run in local mode automatically</description>
    </property>
    <property>
          <name>hive.metastore.warehouse.dir</name>
          <value>cfs:///user/hive/warehouse</value>
          <description>location of default database for the warehouse</description>
    </property>
    <property>
           <name>hive.hwi.war.file</name>
           <value>lib/hive-hwi.war</value>
           <description>This sets the path to the HWI war file, relative to${HIVE_HOME}    </description>
     </property>
     <property>
            <name>hive.metastore.rawstore.impl</name>
          <value>com.datastax.bdp.hadoop.hive.metastore.CassandraHiveMetaStore</value>
            <description>Use the Apache Cassandra Hive RawStore implementation</description>
      </property>
      <property>
             <name>hadoop.bin.path</name>
             <value>${dse.bin}/dse hadoop</value>
       </property>
       <!-- Set this to true to enable auto-creation of Cassandra keyspaces as Hive Databases -->
      <property>
            <name>cassandra.autoCreateHiveSchema</name>
           <value>true</value>
       </property>
  </configuration>

Can anyone please suggest something. where I'm wrong or missing anything.

Answer 1

There is a libthrift version conflict in WSO2 DSS 3.2.2+. They include a libthrift jar in their deployment and it is loaded before any you put in the components\\lib directory. They have an updated libthrift with the right interfaces. Steps to remediate:

Do a fresh install. Install path will be called $home in this doc

Download libthrift-0.8.0.wso2v1.jar from http://maven.wso2.org/nexus/content/groups/wso2-public/libthrift/wso2/libthrift/0.8.0.wso2v1/

Set the windows environmental variable CLASSPATH to $\\home\\repository\\components\\lib (this may not be necessary)

Copy the libthrift 0.8 to $home\\repository\\components\\plugins. Remove the libthift 0.7 jar

Edit $home\\repository\\components\\features\\org.wso2.carbon.logging.mgt.server_4.2.1. For the libthrift line make it end in version="0.8.0.wso2v2"

Edit $home\\repository\\components\\features\\org.wso2.carbon.databridge.commons.thrift.server_4.2.0 . Change the version of libthrift there as well.

Answer 2

I think you are missing some of the HiveServer2 JDBC jar files and dependencies. Link https://cwiki.apache.org/confluence/display/Hive/HiveServer2+Clients has the documents about jar files you need to add to your class path.