Iceberg 基础：修订间差异
跳到导航
跳到搜索
（创建页面，内容为“=== hive -> iceberg === ==== hive ==== <small><nowiki># 分隔符为空格，字符串中有空格用双引号引起来 CREATE TABLE test1 ( col1 STRING, col2 INT, col3 STRING, col4 STRING, col5 STRING ) ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde' WITH SERDEPROPERTIES ( "separatorChar" = " ", "quoteChar" = "\"", "serialization.encoding"="UTF-8" ) STORED AS TEXTFILE; # hdfs dfs -put test1.csv /tmp/data/ LOAD DATA INPATH…”） |
|||
| 第43行： | 第43行： | ||
STORED by iceberg; | STORED by iceberg; | ||
insert into test_ice(col1, col2, col3, col4, col5) select | insert into test_ice(col1, col2, col3, col4, col5) select col1, col2, col3, col4, col5 from test1; | ||
select col4, count(*) cs from test_ice group by col4 limit 10; | select col4, count(*) cs from test_ice group by col4 limit 10; | ||
2024年12月24日 (二) 11:18的版本
hive -> iceberg
hive
# 分隔符为空格，字符串中有空格用双引号引起来
CREATE TABLE test1 (
col1 STRING,
col2 INT,
col3 STRING,
col4 STRING,
col5 STRING
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
WITH SERDEPROPERTIES (
"separatorChar" = " ",
"quoteChar" = "\"",
"serialization.encoding"="UTF-8"
)
STORED AS TEXTFILE;
# hdfs dfs -put test1.csv /tmp/data/
LOAD DATA INPATH '/tmp/data/test1.csv' OVERWRITE INTO TABLE test1;
select col4, count(*) cs from test1 group by col4 limit 10;
----------------------------------------------------------------------------------------------
VERTICES MODE STATUS TOTAL COMPLETED RUNNING PENDING FAILED KILLED
----------------------------------------------------------------------------------------------
Map 1 .......... container SUCCEEDED 30 30 0 0 0 0
Reducer 2 ...... container SUCCEEDED 1 1 0 0 0 0
----------------------------------------------------------------------------------------------
VERTICES: 02/02 [==========================>>] 100% ELAPSED TIME: 99.62 s
----------------------------------------------------------------------------------------------
INFO : Completed executing command(queryId=hdfs_20241224111257_4f4363b0-d489-4bac-99d8-86451fa0a45c); Time taken: 99.725 seconds
iceberg
# 分区字段不能出现在建表字段中
CREATE TABLE test_ice (
col1 STRING,
col2 INT,
col4 STRING,
col5 STRING
)
PARTITIONED BY (col3 STRING)
STORED by iceberg;
insert into test_ice(col1, col2, col3, col4, col5) select col1, col2, col3, col4, col5 from test1;
select col4, count(*) cs from test_ice group by col4 limit 10;
----------------------------------------------------------------------------------------------
VERTICES MODE STATUS TOTAL COMPLETED RUNNING PENDING FAILED KILLED
----------------------------------------------------------------------------------------------
Map 1 .......... container SUCCEEDED 4 4 0 0 0 0
Reducer 2 ...... container SUCCEEDED 1 1 0 0 0 0
----------------------------------------------------------------------------------------------
VERTICES: 02/02 [==========================>>] 100% ELAPSED TIME: 22.68 s
----------------------------------------------------------------------------------------------
INFO : Completed executing command(queryId=hdfs_20241224111143_d436171c-f9fe-4e9a-87e1-0e2ea9b48b1b); Time taken: 26.945 seconds
+----------------+-----------+
| col4 | cs |
+----------------+-----------+
| xeron x5 3708 | 40075712 |
+----------------+-----------+