tencent cloud

hive

beeline -u "jdbc:hive2://${hs2_ip}:${hs2_port}" -n hadoop

mvn archetype:generate -DgroupId=${yourgroupID} -DartifactId=${yourartifactID} -DarchetypeArtifactId=maven-archetype-quickstart

<dependencies>
       <dependency>
           <groupId>org.apache.hive</groupId>
           <artifactId>hive-jdbc</artifactId>
           <version>${hive_version}</version>
       </dependency>
       <dependency>
           <groupId>org.apache.hadoop</groupId>
           <artifactId>hadoop-common</artifactId>
           <version>${hadoop_version}</version>
       </dependency>
</dependencies>

<build>
<plugins>
 <plugin>
   <groupId>org.apache.maven.plugins</groupId>
   <artifactId>maven-compiler-plugin</artifactId>
   <configuration>
     <source>1.8</source>
     <target>1.8</target>
     <encoding>utf-8</encoding>
   </configuration>
 </plugin>
 <plugin>
   <artifactId>maven-assembly-plugin</artifactId>
   <configuration>
     <descriptorRefs>
     <descriptorRef>jar-with-dependencies</descriptorRef>
     </descriptorRefs>
   </configuration>
   <executions>
     <execution>
       <id>make-assembly</id>
       <phase>package</phase>
       <goals>
         <goal>single</goal>
       </goals>
     </execution>
   </executions>
 </plugin>
</plugins>
</build>

package org.example;

import java.sql.*;
/**
 * Created by tencent on 2023/8/11.
 */
public class App {
    private static final String DRIVER_NAME = "org.apache.hive.jdbc.HiveDriver";
    public static void main(String[] args) throws SQLException {
        try {
            // Load hive-jdbc driver
            Class.forName(DRIVER_NAME);
        } catch (ClassNotFoundException e) {
            e.printStackTrace();
            System.exit(1);
        }
        // Get the connection using the provided connection information and account password.
        Connection conn = DriverManager.getConnection("jdbc:hive2://$hs2_ip:$hs2_port/default", "hadoop", "");
        // Create a statement (use conn.prepareStatement(sql) to prevent SQL injection; however, it is mostly used for parameterized SQL execution. For executing different SQL statements in batches, it is recommended to use the following approach).
        Statement stmt = conn.createStatement();
        // The following are basic table creation, data insertion, and data query operations.
        String tableName = "hive_test";
        stmt.execute("drop table if exists " + tableName);
        stmt.execute("create table " + tableName + " (key int, value string)");
        System.out.println("Create table success!");
        // sshow tables
        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 = "describe " + tableName;
        System.out.println("Running: " + sql);
        res = stmt.executeQuery(sql);
        while (res.next()) {
            System.out.println(res.getString(1) + "\\t" + res.getString(2));
        }
        sql = "insert into " + tableName + " values (42,\\"hello\\"),(48,\\"world\\")";
        stmt.execute(sql);
        sql = "select * from " + tableName;
        System.out.println("Running: " + sql);
        res = stmt.executeQuery(sql);
        while (res.next()) {
            System.out.println(res.getInt(1) + "\\t" + res.getString(2));
        }
        sql = "select count(1) from " + tableName;
        System.out.println("Running: " + sql);
        res = stmt.executeQuery(sql);
        while (res.next()) {
            System.out.println(res.getString(1));
        }
    }
}

mvn clean package -DskipTests

scp ${localfile} root@${master_pubilc_ip}:/usr/local/service/hive

yarn jar ./hive-test-1.0-SNAPSHOT-jar-with-dependencies.jar org.example.App

Create table success!
Running: show tables 'hive_test'
hive_test
Running: describe hive_test
key     int
value   string
Running: select * from hive_test
42      hello
48      world
Running: select count(1) from hive_test
2

pip3 install sasl
pip3 install thrift
pip3 install thrift-sasl
pip3 install pyhive

from pyhive import hive

import sys

default_encoding = 'utf-8'

conn = hive.connect(host='${hs2_host}',
                    port='${hs2_port}',
                    username='hadoop',
                    password='hadoop',
                    database='default',
                    auth="CUSTOM",)


tablename = 'HiveByPython'
cur = conn.cursor()

print("\\n")
print('show the tables in default: ')
cur.execute('show tables')
for i in cur.fetchall():
        print(i)

cur.execute('drop table if exists ' + tablename)
cur.execute('create table ' + tablename + ' (key int,value string)')

print("\\n")
print('show the new table: ')
cur.execute('show tables ' +"'" +tablename+"'")
for i in cur.fetchall():
        print(i)

print("\\n")
print("contents from " + tablename + ":")
cur.execute('insert into ' + tablename + ' values (42,"hello"),(48,"world")')
cur.execute('select * from ' + tablename)
for i in cur.fetchall():
        print(i)

python3 hivetest.py

show the tables in default:

show the new table:
('hivebypython',)

contents from HiveByPython:
(42, 'hello')
(48, 'world')