你可以使用Java的HBase API来批量插入数据到HBase 2.0以上版本。当达到2000条数据时,可以一次性插入一批数据。下面是一个示例代码:
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.BufferedMutator;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.util.Bytes;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
public class HBaseExample {
public static void main(String[] args) {
try {
// 创建HBase配置对象
Configuration conf = HBaseConfiguration.create();
conf.set("hbase.zookeeper.quorum", "your_zookeeper_quorum");
conf.set("hbase.zookeeper.property.clientPort", "2181");
// 创建HBase连接对象
Connection connection = ConnectionFactory.createConnection(conf);
// 获取表对象
TableName tableName = TableName.valueOf("your_table_name");
BufferedMutator mutator = connection.getBufferedMutator(tableName);
// 构建要插入的数据
List<Put> putList = new ArrayList<>();
int batchSize = 2000;
int totalRecords = 1000020;
for (int i = 1; i <= totalRecords; i++) {
Put put = new Put(Bytes.toBytes("row_key_" + i));
put.addColumn(Bytes.toBytes("column_family"), Bytes.toBytes("column_qualifier"), Bytes.toBytes("value_" + i));
putList.add(put);
if (i % batchSize == 0) {
mutator.mutate(putList);
mutator.flush();
putList.clear();
}
}
// 插入剩余的数据
if (!putList.isEmpty()) {
mutator.mutate(putList);
mutator.flush();
}
// 关闭资源
mutator.close();
connection.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
请注意,上述代码中的"your_zookeeper_quorum"和"your_table_name"需要替换为你实际的ZooKeeper地址和表名。