dataworks删除大量从hive拉过来的临时表

这些表是通过taskManagement 误操作 拉取了大量hive数仓tmp库中无用的表

在hive中查看表信息找到这个表在hdfs中存储的路径

package data_market;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import java.io.*;
import java.net.URI;

/**
 * 获取hdfs上某个目录下的所有文件夹名称，转化成删除表语句写入本地文本
 */
public class HDFSApp {
    public static void main(String[] args) throws Exception {

        Configuration configuration = new Configuration();
        FileSystem fileSystem = FileSystem.get(new URI("hdfs://xxx.cluste:8020"), configuration, "xxx");
        FileStatus[] statuses = fileSystem.listStatus(new Path("/tmp/excel/hive/"));
        FileWriter writer = new FileWriter("/Users/edy/IdeaProjects/ks_bdp_data_process/data_process_spark/src/test/java/data_market/wxt.txt");

        for(FileStatus file : statuses) {
            String path = file.getPath().toString();
            String[] split = path.split("hdfs://xxx-1.cluste:8020/tmp/excel/hive/tmp.");
            String sql = "drop table if exists kaishu_bigdata_dev." + split[1] + ";";

            try {
                writer.write(sql+"\r\n");
                writer.flush();
               // writer.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }

}

生成的文本文件

最后复制粘贴到dataworks上运行，删除表