Hive第二天学习内容总结Hive 第三天DDL特别注意一下，没事别删除数据DML

Hive SQL Language Manual:  Commands, CLIs, Data Types,
DDL (create/drop/alter/truncate/show/describe), Statistics (analyze), Indexes, Archiving,
DML (load/insert/update/delete/merge, import/export, explain plan),
Queries (select), Operators and UDFs, Locks, Authorization
File Formats and Compression:  RCFile, Avro, ORC, Parquet; Compression, LZO
Procedural Language:  Hive HPL/SQL
Hive Configuration Properties
Hive Clients
Hive Client (JDBC, ODBC, Thrift)
HiveServer2:  Overview, HiveServer2 Client and Beeline, Hive Metrics

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)

Standard syntax:
INSERT OVERWRITE TABLE tablename1 [PARTITION (partcol1=val1, partcol2=val2 ...) [IF NOT EXISTS]] select_statement1 FROM from_statement;
INSERT INTO TABLE tablename1 [PARTITION (partcol1=val1, partcol2=val2 ...)] select_statement1 FROM from_statement;
 
Hive extension (multiple inserts):
FROM from_statement
INSERT OVERWRITE TABLE tablename1 [PARTITION (partcol1=val1, partcol2=val2 ...) [IF NOT EXISTS]] select_statement1
[INSERT OVERWRITE TABLE tablename2 [PARTITION ... [IF NOT EXISTS]] select_statement2]
[INSERT INTO TABLE tablename2 [PARTITION ...] select_statement2] ...;
FROM from_statement
INSERT INTO TABLE tablename1 [PARTITION (partcol1=val1, partcol2=val2 ...)] select_statement1
[INSERT INTO TABLE tablename2 [PARTITION ...] select_statement2]
[INSERT OVERWRITE TABLE tablename2 [PARTITION ... [IF NOT EXISTS]] select_statement2] ...;
 
Hive extension (dynamic partition inserts):
INSERT OVERWRITE TABLE tablename PARTITION (partcol1[=val1], partcol2[=val2] ...) select_statement FROM from_statement;
INSERT INTO TABLE tablename PARTITION (partcol1[=val1], partcol2[=val2] ...) select_statement FROM from_statement;

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.cnt

Standard Syntax:
INSERT INTO TABLE tablename [PARTITION (partcol1[=val1], partcol2[=val2] ...)] VALUES values_row [, values_row ...]
 
Where values_row is:
( value [, value ...] )
where a value is either null or any valid SQL literal

CREATE TABLE students (name VARCHAR(64), age INT, gpa DECIMAL(3, 2))
  CLUSTERED BY (age) INTO 2 BUCKETS STORED AS ORC;
 
INSERT INTO TABLE students
  VALUES ('fred flintstone', 35, 1.28), ('barney rubble', 32, 2.32);
  
CREATE TABLE pageviews (userid VARCHAR(64), link STRING, came_from STRING)
  PARTITIONED BY (datestamp STRING) CLUSTERED BY (userid) INTO 256 BUCKETS STORED AS ORC;
 
INSERT INTO TABLE pageviews PARTITION (datestamp = '2014-09-23')
  VALUES ('jsmith', 'mail.com', 'sports.com'), ('jdoe', 'mail.com', null);
 
INSERT INTO TABLE pageviews PARTITION (datestamp)
  VALUES ('tjohnson', 'sports.com', 'finance.com', '2014-09-23'), ('tlee', 'finance.com', null, '2014-09-21');