HiveQL简单操作DDL

hive-version2.1.1

DDL操作

Create/Drop/Alter/Use Database

创建数据库

 //官方指导
 CREATE (DATABASE|SCHEMA) [IF NOT EXISTS] database_name
   [COMMENT database_comment]
   [LOCATION hdfs_path]
   [WITH DBPROPERTIES (property_name=property_value, ...)];

//示例 create database if not exists testdb；

删除数据库

 //官方指导
 DROP (DATABASE|SCHEMA) [IF EXISTS] database_name [RESTRICT|CASCADE];

//示例 drop database testdb;

说明：restrict不跟参数为默认参数，如果数据库不为空，则会删除失败；

　　　cascade 如果数据库有表时也要删除。

修改数据库

 //官方指导
 ALTER (DATABASE|SCHEMA) database_name SET DBPROPERTIES (property_name=property_value, ...);   -- (Note: SCHEMA added in Hive 0.14.0)

 ALTER (DATABASE|SCHEMA) database_name SET OWNER [USER|ROLE] user_or_role;   -- (Note: Hive 0.13.0 and later; SCHEMA added in Hive 0.14.0)

 ALTER (DATABASE|SCHEMA) database_name SET LOCATION hdfs_path; -- (Note: Hive 2.2.1, 2.4.0 and later)

 //示例1 set dbproperties 设置数据库属性
 alter database testdb set dbproperties('name'='xiaoming'); 

  //示例2 set owner 修改所属者名字和类型
  alter database testdb set owner user root;

说明：SET LOCATION要2.2.1，2.4.0及更高版本才支持，不会更改数据库现有的内容的位置，创建新表时新表父目录会更改。

使用数据库

 //官方指导 USE database_name; USE DEFAULT;

//示例USE testdb;

Create/Drop/Truncate Table

创建表

 //官方指导
 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 [TEMPORARY] [EXTERNAL] TABLE [IF NOT EXISTS] [db_name.]table_name
   LIKE existing_table_or_view_name
   [LOCATION hdfs_path];

 data_type
   : primitive_type
   | array_type
   | map_type
   | struct_type
   | union_type  -- (Note: Available in Hive 0.7.0 and later)

 primitive_type
   : TINYINT
   | SMALLINT
   | INT
   | BIGINT
   | BOOLEAN
   | FLOAT
   | DOUBLE
   | DOUBLE PRECISION -- (Note: Available in Hive 2.2.0 and later)
   | STRING
   | BINARY      -- (Note: Available in Hive 0.8.0 and later)
   | TIMESTAMP   -- (Note: Available in Hive 0.8.0 and later)
   | DECIMAL     -- (Note: Available in Hive 0.11.0 and later)
   | DECIMAL(precision, scale)  -- (Note: Available in Hive 0.13.0 and later)
   | DATE        -- (Note: Available in Hive 0.12.0 and later)
   | VARCHAR     -- (Note: Available in Hive 0.12.0 and later)
   | CHAR        -- (Note: Available in Hive 0.13.0 and later)

 array_type
   : ARRAY < data_type >

 map_type
   : MAP < primitive_type, data_type >

 struct_type
   : STRUCT < col_name : data_type [COMMENT col_comment], ...>

 union_type
    : UNIONTYPE < data_type, data_type, ... >  -- (Note: Available in Hive 0.7.0 and later)

 row_format
   : DELIMITED [FIELDS TERMINATED BY char [ESCAPED BY char]] [COLLECTION ITEMS TERMINATED BY char]
         [MAP KEYS TERMINATED BY char] [LINES TERMINATED BY char]
         [NULL DEFINED AS char]   -- (Note: Available in Hive 0.13 and later)
   | SERDE serde_name [WITH SERDEPROPERTIES (property_name=property_value, property_name=property_value, ...)]

 file_format:
   : SEQUENCEFILE
   | TEXTFILE    -- (Default, depending on hive.default.fileformat configuration)
   | RCFILE      -- (Note: Available in Hive 0.6.0 and later)
   | ORC         -- (Note: Available in Hive 0.11.0 and later)
   | PARQUET     -- (Note: Available in Hive 0.13.0 and later)
   | AVRO        -- (Note: Available in Hive 0.14.0 and later)
   | INPUTFORMAT input_format_classname OUTPUTFORMAT output_format_classname

 constraint_specification:
   : [, PRIMARY KEY (col_name, ...) DISABLE NOVALIDATE ]
     [, CONSTRAINT constraint_name FOREIGN KEY (col_name, ...) REFERENCES table_name(col_name, ...) DISABLE NOVALIDATE 

 //示例 外部分区表
  create external table if not exists testdb.test
   (id int COMMENT '这是主键',
  ad array<String>,
  bd map<string,String>,
  cd struct<a:String,b:string,c:string,d:String>)
  COMMENT '这是测试表'
  partitioned by(dd String,time String)
  row format delimited
  fields terminated by  '\u0001'
  collection items terminated by  ','
  map keys terminated by  ':'
  lines terminated by '\n'
  location '/use/';

说明:external 创建一张表不使用hive默认位置，可以指向hdfs任何位置，也就是外部表

　　partitioned 分区字段

　　fields terminated by 字段分割方式

　　collection items terminated by   array，map，struct特殊字段中数据分割方式

　　map keys terminated by  map中key：value的分割方式

　　stored as textfile location 指定外部表数据的位置

还可以创建排序表，倾斜表，临时表以及加约束条件

TEMPORARY临时表现在还不支持分区

分桶表

create external table if not exists ods_db_poker.tb_player (`id` int COMMENT '主键',`playerName` string,updateTime bigint COMMENT '跟新时间') partitioned by(currentDate int COMMENT '当前日期')  CLUSTERED BY(id) SORTED BY(updateTime) INTO 10 BUCKETS row format delimited fields terminated by  '\u0001' lines terminated by '\n' location '/warehouse/tablespace/external/hive/ods_db_poker.db/tb_player'

CLUSTERED BY 分桶字段,根据改字段取hash分桶

SORTED BY 排序字段,根据该字段做升降序排序

INTO 10 BUCKETS  分桶个数 10

RegEx/JSON/CSV/TSV

//官方指导
//正则表达式 regex
CREATE TABLE apachelog (
  host STRING,
  identity STRING,
  user STRING,
  time STRING,
  request STRING,
  status STRING,
  size STRING,
  referer STRING,
  agent STRING)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe'
WITH SERDEPROPERTIES (
  "input.regex" = "([^]*) ([^]*) ([^]*) (-|\\[^\\]*\\]) ([^ \"]*|\"[^\"]*\") (-|[0-9]*) (-|[0-9]*)(?: ([^ \"]*|\".*\") ([^ \"]*|\".*\"))?"
)
STORED AS TEXTFILE;
//json字符串

ADD JAR /usr/lib/hive-hcatalog/lib/hive-hcatalog-core.jar;

CREATE TABLE my_table(a string, b bigint, ...)
ROW FORMAT SERDE 'org.apache.hive.hcatalog.data.JsonSerDe'
STORED AS TEXTFILE;
// CSV / TSV格式
CREATE TABLE my_table(a string, b string, ...)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
WITH SERDEPROPERTIES (
   "separatorChar" = "\t",
   "quoteChar"     = "'",
   "escapeChar"    = "\\"
)
STORED AS TEXTFILE;

//示例 json
//加入jar

add jar /root/hive-json-serde-0.2.jar;
add jar /root/hive-hcatalog-core-2.1.1.jar;

//sql

CREATE TABLE my_table(name string, url string) partitioned by(time String) ROW FORMAT SERDE 'org.apache.hive.hcatalog.data.JsonSerDe';

删除表

 //官方指导
 DROP TABLE [IF EXISTS] table_name [PURGE];     -- (Note: PURGE available in Hive 0.14.0 and later)

 //示例
 drop table  testdb.test;

说明：PURGE 在配置了垃圾回收站的情况下，如果指定此参数，数据将会直接删除。否则将移至垃圾回收目录。

截断表

 //官方指导
 TRUNCATE TABLE table_name [PARTITION partition_spec];

 partition_spec:
   : (partition_column = partition_col_value, partition_column = partition_col_value, ...)

 //示例
 truncate table testdb.test partition(time=2017);

说明：删除该分区中所有数据，可以同时删除多个分区中的数据，分区依旧存在。

Alter Table/Partition/Column

重命名表

 //官方指导
 ALTER TABLE table_name RENAME TO new_table_name;

 //示例
 alter table testdb.test rename to testone;

更改表属性

 //官方指导
 ALTER TABLE table_name SET TBLPROPERTIES table_properties;

 table_properties:
   : (property_name = property_value, property_name = property_value, ... )

 //示例
 alter table testdb.testone set tblproperties('propertyone'='第一个测试');

说明： 设置自己的元数据

添加serdo属性

 //官方指导
 ALTER TABLE table_name [PARTITION partition_spec] SET SERDE serde_class_name [WITH SERDEPROPERTIES serde_properties];

 ALTER TABLE table_name [PARTITION partition_spec] SET SERDEPROPERTIES serde_properties;

 serde_properties:
   : (property_name = property_value, property_name = property_value, ... )

 //示例
 alter table testdb.testone set serdeproperties('test'='test');

添加分区

 //官方指导
 ALTER TABLE table_name ADD [IF NOT EXISTS] PARTITION partition_spec [LOCATION 'location'][, PARTITION partition_spec [LOCATION 'location'], ...];

 partition_spec:
   : (partition_column = partition_col_value, partition_column = partition_col_value, ...)

 //示例 
2 　alter table testdb.test add partition (dd='10',time='2020') location '/root/a.txt';

向多分区表加分区时，必须指定在那个分区中；

动态分区

 //官方指导
 FROM page_view_stg pvs
 INSERT OVERWRITE TABLE page_view PARTITION(dt='2008-06-08', country)
        SELECT pvs.viewTime, pvs.userid, pvs.page_url, pvs.referrer_url, null, null, pvs.ip, pvs.country

 //示例
 //修改配置文件hive-site
 //hive.exec.dynamic.partition=true;
 //hive.exec.dynamic.partition.mode=nonstrict;
 insert overwrite table test1  partition(dd,time) select id,ad,bd,cd,dd,time  from test;

重命名分区

 //官方指导
 ALTER TABLE table_name PARTITION partition_spec RENAME TO PARTITION partition_spec;

 //示例
 ALTER TABLE test PARTITION(dd='a',time='') RENAME TO PARTITION(dd='a',time='');

多个分区时必须指定不改变的分区，支持同时修改

删除分区

//官方指导
ALTER TABLE table_name DROP [IF EXISTS] PARTITION partition_spec[, PARTITION partition_spec, ...]
  [IGNORE PROTECTION] [PURGE];            -- (Note: PURGE available in Hive 1.2.0 and later, IGNORE PROTECTION not available 2.0.0 and later)

 //示例
 alter table testdb.test drop  partition (dd = 'a');

修改分区或表文件格式

 //官方指导
 ALTER TABLE table_name [PARTITION partition_spec] SET FILEFORMAT file_format;

 // 示例 一般都用text
 alter table test partition (dd='b') set fileformat rcfile;

改变列

更改列名/类型/位置/注释

 //官方指导
 ALTER TABLE table_name [PARTITION partition_spec] CHANGE [COLUMN] col_old_name col_new_name column_type
   [COMMENT col_comment] [FIRST|AFTER column_name] [CASCADE|RESTRICT];

//示例 id 改为id1 类型int 放在第1位 first
alter table test  change id  id1 int first;

添加或替换列

 //官方指导
 ALTER TABLE table_name
   [PARTITION partition_spec]                 -- (Note: Hive 0.14.0 and later)
   ADD|REPLACE COLUMNS (col_name data_type [COMMENT col_comment], ...)
   [CASCADE|RESTRICT]                         -- (Note: Hive 1.1.0 and later)

 //示例
 alter table test add columns(ed string);

视图、索引、权限等DDL操作请参考apache Hive官方文档