目前看，数据这边没有太好的办法测试，只能自己去构造测试数据了。考虑还是从java客户端，插hive，然后跑job。跑完之后，查看结果。

pom.xml

• 注意，hive-jdbc版本不要太高，要跟服务器端的一致，选择1.1.0比较稳妥，否则会报错的。
• 另外需要引入hadoop-common，否则会报java.lang.NoClassDefFoundError: org/apache/hadoop/conf/Configuration

<dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter</artifactId>
        </dependency>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
            <exclusions>
                <exclusion>
                    <groupId>org.junit.vintage</groupId>
                    <artifactId>junit-vintage-engine</artifactId>
                </exclusion>
            </exclusions>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hive/hive-jdbc -->
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-jdbc</artifactId>
            <version>1.1.0</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>3.2.1</version>
        </dependency>
    </dependencies>

JAVA代码

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

    /**
     * @param args
     * @throws SQLException
     */
    public static void main(String[] args) throws SQLException {
        try {
            Class.forName(driverName);
        } catch (ClassNotFoundException e) {
            e.printStackTrace();
            System.exit(1);
        }
        //replace "hive" here with the name of the user the queries should run as
        Connection con = DriverManager.getConnection("jdbc:hive2://localhost:10000/default", "hive", "");
        Statement stmt = con.createStatement();
        String tableName = "testHiveDriverTable";
        stmt.execute("drop table if exists " + tableName);
        stmt.execute("create table " + tableName + " (key int, value string)");
        // show 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));
        }

        // select * query
        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));
        }

        // 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));
        }
    }
}

运行结果

image.png

从文件导入

        // 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
        // 必须是服务器上的路径，要先上传到服务器上面才行
        String filepath = "/tmp/a.txt";
        sql = "load data local inpath '" + filepath + "' into table " + tableName;
        System.out.println("Running: " + sql);
        stmt.execute(sql);