Question

我正在尝试使用JDBC驱动程序访问HIVE表。当我尝试使用maven执行该类时，执行会挂起并在控制台上永远保持它。以下是我尝试运行该类时的控制台输出： -

hduser@localhost:~/workspace/FetchHiveData$ mvn exec:java -Dexec.mainClass=HiveJdbcClient
[INFO] Scanning for projects...
[WARNING] 
[WARNING] Some problems were encountered while building the effective model for FetchHiveData:FetchHiveData:jar:1.0
[WARNING] 'dependencies.dependency.(groupId:artifactId:type:classifier)' must be unique: org.apache.spark:spark-mllib_2.10:jar -> duplicate declaration of version 1.1.0 @ line 54, column 15
[WARNING] 
[WARNING] It is highly recommended to fix these problems because they threaten the stability of your build.
[WARNING] 
[WARNING] For this reason, future Maven versions might no longer support building such malformed projects.
[WARNING] 
[INFO]                                                                         
[INFO] ------------------------------------------------------------------------
[INFO] Building FetchHiveData 1.0
[INFO] ------------------------------------------------------------------------
[INFO] 
[INFO] --- exec-maven-plugin:1.3.2:java (default-cli) @ FetchHiveData ---
Initialising Connection...********************************
log4j:WARN No appenders could be found for logger (org.apache.hive.jdbc.Utils).
log4j:WARN Please initialize the log4j system properly.
log4j:WARN See http://logging.apache.org/log4j/1.2/faq.html#noconfig for more info.

我已经启动了我的Hive thrift服务器并且它正在工作，因为我能够使用JSON文件将数据ETL到它中。

这是我正在通过JDBC连接到HIVE的类： -

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.hive.jdbc.HiveDriver";

  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);
}
System.out.println("Initialising Connection...********************************"); 
Connection con =   DriverManager.getConnection("jdbc:hive2://localhost:9083/default", "", "");
System.out.println("Connection made*******************************");  
Statement stmt = con.createStatement();
String tableName = "people_spark_him3";
String sql = "show tables '" + tableName + "'";
System.out.println("Running: " + sql);
ResultSet res = stmt.executeQuery(sql);
if (res.next()) {
  System.out.println(res.getString(1));
}
// describe table
sql = "select * from " + tableName;
System.out.println("Running: " + sql);
res = stmt.executeQuery(sql);
while (res.next()) {
  System.out.println(res.getString(1) + "\t" + res.getString(2));
}
}
}

这是我的POM： -

<dependencies>
    <dependency>
        <groupId>org.apache.hive</groupId>
        <artifactId>hive-jdbc</artifactId>
        <version>1.1.0</version>
    </dependency>
    <dependency>
        <groupId>org.scala-lang</groupId>
        <artifactId>scala-library</artifactId>
        <version>2.10.4</version>
    </dependency>
    <dependency>
        <groupId>junit</groupId>
        <artifactId>junit</artifactId>
        <version>4.11</version>
        <scope>test</scope>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-core_2.10</artifactId>
        <version>1.2.1</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-streaming_2.10</artifactId>
        <version>1.1.0</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-sql_2.10</artifactId>
        <version>1.2.1</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-hive_2.10</artifactId>
        <version>1.2.1</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-mllib_2.10</artifactId>
        <version>1.1.0</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-graphx_2.10</artifactId>
        <version>1.1.0</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-mllib_2.10</artifactId>
        <version>1.1.0</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-streaming-twitter_2.10</artifactId>
        <version>1.1.0</version>
    </dependency>
    <dependency>
        <groupId>org.twitter4j</groupId>
        <artifactId>twitter4j-core</artifactId>
        <version>3.0.6</version>
    </dependency>
    <dependency>
        <groupId>org.twitter4j</groupId>
        <artifactId>twitter4j-stream</artifactId>
        <version>3.0.6</version>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-streaming-kafka_2.10</artifactId>
        <version>1.1.0</version>
    </dependency>
</dependencies>
<build>
    <plugins>
        <plugin>
            <groupId>org.codehaus.mojo</groupId>
            <artifactId>exec-maven-plugin</artifactId>
            <version>1.2.1</version>
            <executions>
                <execution>
                    <goals>
                        <goal>java</goal>
                    </goals>
                </execution>
            </executions>
            <configuration>
                <mainClass>HiveJdbcClient</mainClass>
            </configuration>
        </plugin>
        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-compiler-plugin</artifactId>
            <configuration>
                <source>1.6</source>
                <target>1.6</target>
                <optimize>true</optimize>
            </configuration>
        </plugin>
    </plugins>
</build>

Hive JDBC程序静默挂起，因为getConnection方法不返回

0 个答案: