Hive Data Definition Language

-- 创建test库
create database if not exists test
        comment ‘Test database‘
        location ‘/user/hive/test‘
        with dbproperties(
                ‘Date‘ = ‘2018-08-22‘,
                ‘Creator‘ = ‘ylh‘
                );

-- 显示test库
show databases like ‘test*‘;

-- 查看test库信息
desc database test;
desc database extended test;

-- 使用test库
use test;

-- 删除test库
drop database if exists test restrict/cascade;

CREATE [TEMPORARY] [EXTERNAL] TABLE [IF NOT EXISTS] [db_name.]table_name    -- (Note: TEMPORARY available in Hive 0.14.0 and later)
  [(col_name data_type [COMMENT col_comment], ... [constraint_specification])]
  [COMMENT table_comment]
  [PARTITIONED BY (col_name data_type [COMMENT col_comment], ...)]
  [CLUSTERED BY (col_name, col_name, ...) [SORTED BY (col_name [ASC|DESC], ...)] INTO num_buckets BUCKETS]
  [SKEWED BY (col_name, col_name, ...)                  -- (Note: Available in Hive 0.10.0 and later)]
     ON ((col_value, col_value, ...), (col_value, col_value, ...), ...)
     [STORED AS DIRECTORIES]
  [
   [ROW FORMAT row_format] 
   [STORED AS file_format]
     | STORED BY ‘storage.handler.class.name‘ [WITH SERDEPROPERTIES (...)]  -- (Note: Available in Hive 0.6.0 and later)
  ]
  [LOCATION hdfs_path]
  [TBLPROPERTIES (property_name=property_value, ...)]   -- (Note: Available in Hive 0.6.0 and later)
  [AS select_statement];   -- (Note: Available in Hive 0.5.0 and later; not supported for external tables)

CREATE EXTERNAL TABLE IF NOT EXISTS user (
  first_name STRING(64),
  last_name STRING(64),
  company_name STRING(64),
  address STRUCT<zip:INT, street:STRING>,
  country STRING(64),
  city STRING(32),
  state STRING(32),
  post INT,
  phone_nos ARRAY<STRING>,
  mail MAP<STRING, STRING>,
  web_address STRING(64)
  )
  ROW FORMAT DELIMITED 
    FIELDS TERMINATED BY ‘,‘
    COLLECTION ITEMS TERMINATED BY ‘\t‘
    MAP KEYS TERMINATED BY ‘:‘
    LINES TERMINATED BY ‘\n‘
  STORED AS TEXTFILE;
 
LOAD DATA LOCAL INPATH ‘/home/user/User_Records.txt‘ OVERWRITE INTO TABLE user;
 
SELECT * FROM user;

CREATE TABLE new_key_value_store
   ROW FORMAT SERDE "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe"
   STORED AS RCFile
   AS
SELECT (key % 1024) new_key, concat(key, value) key_value_pair
FROM key_value_store
SORT BY new_key, key_value_pair;

CREATE EXTERNAL TABLE IF NOT EXISTS test_db.user 
 LIKE default.user
        LOCATION ‘/user/hive/usertable‘
        ;
 
INSERT OVERWRITE TABLE test_db.user SELECT * FROM default.user;
 
SELECT first_name, city, mail FROM test_db.user WHERE country=‘AU‘;

CREATE TABLE page_view(viewTime INT, userid BIGINT,
     page_url STRING, referrer_url STRING,
     ip STRING COMMENT ‘IP Address of the User‘)
 COMMENT ‘This is the page view table‘
 PARTITIONED BY(dt STRING, country STRING)
 CLUSTERED BY(userid) SORTED BY(viewTime) INTO 32 BUCKETS
 ROW FORMAT DELIMITED
   FIELDS TERMINATED BY ‘\001‘
   COLLECTION ITEMS TERMINATED BY ‘\002‘
   MAP KEYS TERMINATED BY ‘\003‘
 STORED AS SEQUENCEFILE;

CREATE TABLE list_bucket_single (
  key STRING, 
  value STRING
  )
SKEWED BY (key) ON (1,5,6) [STORED AS DIRECTORIES];

CREATE TABLE list_bucket_multiple (
  col1 STRING, 
  col2 int, 
  col3 STRING)
SKEWED BY (col1, col2) ON ((‘s1‘,1), (‘s3‘,3), (‘s13‘,13), (‘s78‘,78)) [STORED AS DIRECTORIES];