从Hive表中导出数据到文件

1. 保存结果到本地

   方法一：通过重定向方式,将查询结果写到指定的文件中

   hive -e "SELECT id,concat_ws(',',collect_set(concat(k1,'-',k2,'-',k3))) from test.users GROUP BY id;" > users.data
   

   查看

   [root@node00 ~]# cat users.data 
   1	a1-a2-a3,a11-a22-a33,a111-a222-a333
   2	b1-b2-b3,b11-b22-b33
   

   方法二：使用INSERT OVERWRITE LOCAL DIRECTORY保存结果到本地

   hive -e "
   INSERT OVERWRITE LOCAL DIRECTORY '/home/charles/users.data' 
   ROW format delimited fields terminated BY '\t' 
   SELECT id,concat_ws(',',collect_set(concat(k1,'-',k2,'-',k3))) from test.users GROUP BY id;
   "
   

   查看

   [root@node00 charles]# ll -a users.data
   total 16
   -rw-r--r-- 1 root root   61 May  9 17:24 000000_0
   -rw-r--r-- 1 root root   12 May  9 17:24 .000000_0.crc
   [root@node00 charles]# cat users.data/000000_0 
   1	a1-a2-a3,a11-a22-a33,a111-a222-a333
   2	b1-b2-b3,b11-b22-b33
   

   方法三：使用Hadoop命令保存结果到本地

   [root@cdh01 ~]# hdfs dfs -get /user/hive/warehouse/test /root/test;
   

   查看

   [root@cdh01 ~]# cat /root/test/data.txt
   {"one":true,"three":["red","yellow","orange"],"two":19.5,"four":"poop"}
   {"one":false,"three":["red","yellow","black"],"two":129.5,"four":"stars"}
   {"one":false,"three":["pink","gold"],"two":222.56,"four":"fiat"}
   

   方法四：利用 Sqoop 导出 Hive 表

2. 保存结果到HDFS中

   方法一：使用INSERT OVERWRITE DIRECTORY命令保存结果到HDFS

   hive -e "
   INSERT OVERWRITE DIRECTORY '/users.data' 
   ROW format delimited fields terminated BY '\t' 
   SELECT id,concat_ws(',',collect_set(concat(k1,'-',k2,'-',k3))) from test.users GROUP BY id;
   "
   

   查看

   [root@node00 ~]# hdfs dfs -ls /users.data
   Found 1 items
   -rwxrwxrwx   3 root supergroup         61 2019-05-09 17:28 /users.data/000000_0
   [root@node00 ~]# hdfs dfs -cat /users.data/000000_0
   1	a1-a2-a3,a11-a22-a33,a111-a222-a333
   2	b1-b2-b3,b11-b22-b33
   

   方法二：使用export命令保存结果到HDFS

   hive> export table default.test to '/root/test/';
   Copying data from file:/tmp/hdfs/849dfd20-a5df-4994-a5fa-2aa44c28f5dc/hive_2019-07-19_23-13-00_527_6322373220241253473-1/-local-10000/_metadata
   Copying file: file:/tmp/hdfs/849dfd20-a5df-4994-a5fa-2aa44c28f5dc/hive_2019-07-19_23-13-00_527_6322373220241253473-1/-local-10000/_metadata
   Copying data from hdfs://cdh01.cnyimi.cn:8020/user/hive/warehouse/test
   Copying file: hdfs://cdh01.cnyimi.cn:8020/user/hive/warehouse/test/data.txt
   OK
   

   查看

   [root@cdh01 ~]# hdfs dfs -cat /root/test/_metadata
   {"version":"0.1","table":"{\"1\":{\"str\":\"test\"},\"2\":{\"str\":\"default\"},\"3\":{\"str\":\"root\"},\"4\":{\"i32\":1561560428},\"5\":{\"i32\":0},\"6\":{\"i32\":0},\"7\":{\"rec\":{\"1\":{\"lst\":[\"rec\",4,{\"1\":{\"str\":\"one\"},\"2\":{\"str\":\"boolean\"}},{\"1\":{\"str\":\"three\"},\"2\":{\"str\":\"array<string>\"}},{\"1\":{\"str\":\"two\"},\"2\":{\"str\":\"double\"}},{\"1\":{\"str\":\"four\"},\"2\":{\"str\":\"string\"}}]},\"2\":{\"str\":\"hdfs://cdh01.cnyimi.cn:8020/user/hive/warehouse/test\"},\"3\":{\"str\":\"org.apache.hadoop.mapred.TextInputFormat\"},\"4\":{\"str\":\"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat\"},\"5\":{\"tf\":0},\"6\":{\"i32\":-1},\"7\":{\"rec\":{\"2\":{\"str\":\"org.openx.data.jsonserde.JsonSerDe\"},\"3\":{\"map\":[\"str\",\"str\",1,{\"serialization.format\":\"1\"}]}}},\"8\":{\"lst\":[\"str\",0]},\"9\":{\"lst\":[\"rec\",0]},\"10\":{\"map\":[\"str\",\"str\",0,{}]},\"11\":{\"rec\":{\"1\":{\"lst\":[\"str\",0]},\"2\":{\"lst\":[\"lst\",0]},\"3\":{\"map\":[\"lst\",\"str\",0,{}]}}},\"12\":{\"tf\":0}}},\"8\":{\"lst\":[\"rec\",0]},\"9\":{\"map\":[\"str\",\"str\",6,{\"totalSize\":\"211\",\"numRows\":\"0\",\"rawDataSize\":\"0\",\"numFiles\":\"1\",\"transient_lastDdlTime\":\"1561560623\",\"numFilesErasureCoded\":\"0\"}]},\"12\":{\"str\":\"MANAGED_TABLE\"},\"15\":{\"i32\":1}}","partitions":[]}
   [root@cdh01 ~]# hdfs dfs -cat /root/test/data/data.txt
   {"one":true,"three":["red","yellow","orange"],"two":19.5,"four":"poop"}
   {"one":false,"three":["red","yellow","black"],"two":129.5,"four":"stars"}
   {"one":false,"three":["pink","gold"],"two":222.56,"four":"fiat"}