吴超老师课程--Hive的执行语句

CREATE TABLE tmp_table #表名
(
title   string, # 字段名称 字段类型
minimum_bid     double,
quantity        bigint,
have_invoice    bigint
)COMMENT ‘注释：XXX‘ #表注释
 PARTITIONED BY(pt STRING) #分区表字段（如果你文件非常之大的话，采用分区表可以快过滤出按分区字段划分的数据）
 ROW FORMAT DELIMITED 
   FIELDS TERMINATED BY ‘\001‘   # 字段是用什么分割开的
STORED AS SEQUENCEFILE; #用哪种方式存储数据，SEQUENCEFILE是hadoop自带的文件压缩格式

一些相关命令
SHOW TABLES; # 查看所有的表
SHOW TABLES ‘*TMP*‘; #支持模糊查询
SHOW PARTITIONS TMP_TABLE; #查看表有哪些分区
DESCRIBE TMP_TABLE; #查看表结构

创建数据文件partition_table.dat
创建表
create table partition_table(rectime string,msisdn string) partitioned by(daytime string,city string) row format delimited fields terminated by ‘\t‘ stored as TEXTFILE;
加载数据到分区
load data local inpath ‘/home/partition_table.dat‘ into table partition_table partition (daytime=‘2013-02-01‘,city=‘bj‘);
查看数据
select * from partition_table
select count(*) from partition_table
•删除表 drop table partition_table

alter table partition_table add partition (daytime=‘2013-02-04‘,city=‘bj‘);
通过load data 加载数据

alter table partition_table drop partition (daytime=‘2013-02-04‘,city=‘bj‘)
元数据，数据文件删除，但目录daytime=2013-02-04还在

创建表
    create table bucket_table(id string) clustered by(id) into 4 buckets;        
加载数据
    set hive.enforce.bucketing = true;
    insert into table bucket_table select name from stu;    
    insert overwrite table bucket_table select name from stu;
数据加载到桶表时，会对字段取hash值，然后与桶的数量取模。把数据放到对应的文件中。

抽样查询
    select * from bucket_table tablesample(bucket 1 out of 4 on id);

CREATE EXTERNAL TABLE page_view
( viewTime INT, 
  userid BIGINT,
  page_url STRING,     
 referrer_url STRING,                             
  ip STRING COMMENT ‘IP Address of the User‘,
  country STRING COMMENT ‘country of origination‘
)
    COMMENT ‘This is the staging page view table‘
    ROW FORMAT DELIMITED FIELDS TERMINATED BY ‘44‘ LINES     TERMINATED BY ‘12‘
    STORED AS TEXTFILE
    LOCATION ‘hdfs://centos:9000/user/data/staging/page_view‘;

创建数据文件external_table.dat

创建表
hive>create external table external_table1 (key string) ROW FORMAT DELIMITED FIELDS TERMINATED BY ‘\t‘ location ‘/home/external‘;
在HDFS创建目录/home/external
#hadoop fs -put /home/external_table.dat /home/external

加载数据
LOAD DATA INPATH ‘/home/external_table1.dat‘ INTO TABLE external_table1;

查看数据
select * from external_table
select count(*) from external_table

删除表 
drop table external_table

视图的创建
CREATE VIEW v1 AS select * from t1;

表的修改
alter table target_tab add columns (cols,string)
表的删除
drop table

当数据被加载至表中时，不会对数据进行任何转换。
Load 操作只是将数据复制/移动至 Hive 表对应的位置。
LOAD DATA [LOCAL] INPATH ‘filepath‘ [OVERWRITE]    INTO TABLE tablename    [PARTITION (partcol1=val1, partcol2=val2 ...)]
把一个Hive表导入到另一个已建Hive表
INSERT OVERWRITE TABLE tablename [PARTITION (partcol1=val1, partcol2=val2 ...)] select_statement FROM from_statement
CTAS
CREATE [EXTERNAL] TABLE [IF NOT EXISTS] table_name 
    (col_name data_type, ...)    …
    AS SELECT …
例：create table new_external_test as  select * from external_table1;

select
SELECT [ALL | DISTINCT] select_expr, select_expr, ...
    FROM table_reference 
    [WHERE where_condition] 
    [GROUP BY col_list] 
    [ CLUSTER BY col_list | [DISTRIBUTE BY col_list] [SORT BY col_list] | [ORDER BY col_list] ]
    [LIMIT number]

基于Partition的查询  
一般 SELECT 查询是全表扫描。但如果是分区表，查询就可以利用分区剪枝（input pruning）的特性，类似“分区索引“”，只扫描一个表中它关心的那一部分。
Hive 当前的实现是，只有分区断言（Partitioned by）出现在离 FROM 子句最近的那个WHERE 子句中，才会启用分区剪枝。
例如，如果 page_views 表（按天分区）使用 date 列分区，以下语句只会读取分区为‘2008-03-01’的数据。
 SELECT page_views.*    FROM page_views    WHERE page_views.date >= ‘2013-03-01‘ AND page_views.date <= ‘2013-03-01‘
LIMIT Clause 
Limit 可以限制查询的记录数。查询的结果是随机选择的。
下面的查询语句从 t1 表中随机查询5条记录：
SELECT * FROM t1 LIMIT 5
Top N查询
下面的查询语句查询销售记录最大的 5 个销售代表。
SET mapred.reduce.tasks = 1  SELECT * FROM sales SORT BY amount DESC LIMIT 5                                                                           
   

表连接


导入ac信息表
hive> create table acinfo (name string,acip string)  row format delimited fields terminated by ‘\t‘ stored as TEXTFILE;
hive> load data local inpath ‘/home/acinfo/ac.dat‘ into table acinfo; 
内连接
select b.name,a.* from dim_ac a join acinfo b on (a.ac=b.acip) limit 10;
左外连接
select b.name,a.* from dim_ac a left outer join acinfo b on a.ac=b.acip limit 10;

Hive远程服务启动#hive --service hiveserver >/dev/null  2>/dev/null &
JAVA客户端相关代码
Class.forName("org.apache.hadoop.hive.jdbc.HiveDriver");
Connection con = DriverManager.getConnection("jdbc:hive://192.168.1.102:10000/wlan_dw", "", "");
Statement stmt = con.createStatement();
String querySQL="SELECT * FROM wlan_dw.dim_m order by flux desc limit 10";

ResultSet res = stmt.executeQuery(querySQL);  

while (res.next()) {
System.out.println(res.getString(1) +"\t" +res.getLong(2)+"\t" +res.getLong(3)+"\t" +res.getLong(4)+"\t" +res.getLong(5));
}