hive sql 用法

 

DDL Operations
創建表
hive> CREATE TABLE pokes (foo INT, bar STRING);
創建表並創建索引字段ds
hive> CREATE TABLE invites (foo INT, bar STRING) PARTITIONED BY (ds STRING);
顯示所有表
hive> SHOW TABLES;
按正條件（正則表達式）顯示錶，
hive> SHOW TABLES '.*s';
表添加一列
hive> ALTER TABLE pokes ADD COLUMNS (new_col INT);
添加一列並增加列字段註釋
hive> ALTER TABLE invites ADD COLUMNS (new_col2 INT COMMENT 'a comment');
更改表名
hive> ALTER TABLE events RENAME TO 3koobecaf;
刪除列
hive> DROP TABLE pokes;
元數據存儲
將文件中的數據加載到表中
hive> LOAD DATA LOCAL INPATH './examples/files/kv1.txt' OVERWRITE INTO TABLE pokes;
加載本地數據，同時給定分區信息
hive> LOAD DATA LOCAL INPATH './examples/files/kv2.txt' OVERWRITE INTO TABLE invites PARTITION (ds='2008-08-15');
加載DFS數據 ，同時給定分區信息
hive> LOAD DATA INPATH '/user/myname/kv2.txt' OVERWRITE INTO TABLE invites PARTITION (ds='2008-08-15');
The above command will load data from an HDFS file/directory to the table. Note that loading data from HDFS will result in moving the file/directory. As a result, the operation is almost instantaneous.
SQL 操作
按先件查詢
hive> SELECT a.foo FROM invites a WHERE a.ds='<DATE>';
將查詢數據輸出至目錄
hive> INSERT OVERWRITE DIRECTORY '/tmp/hdfs_out' SELECT a.* FROM invites a WHERE a.ds='<DATE>';
將查詢結果輸出至本地目錄
hive> INSERT OVERWRITE LOCAL DIRECTORY '/tmp/local_out' SELECT a.* FROM pokes a;
選擇所有列到本地目錄
hive> INSERT OVERWRITE TABLE events SELECT a.* FROM profiles a;
hive> INSERT OVERWRITE TABLE events SELECT a.* FROM profiles a WHERE a.key < 100;
hive> INSERT OVERWRITE LOCAL DIRECTORY '/tmp/reg_3' SELECT a.* FROM events a;
hive> INSERT OVERWRITE DIRECTORY '/tmp/reg_4' select a.invites, a.pokes FROM profiles a;
hive> INSERT OVERWRITE DIRECTORY '/tmp/reg_5' SELECT COUNT(1) FROM invites a WHERE a.ds='<DATE>';
hive> INSERT OVERWRITE DIRECTORY '/tmp/reg_5' SELECT a.foo, a.bar FROM invites a;
hive> INSERT OVERWRITE LOCAL DIRECTORY '/tmp/sum' SELECT SUM(a.pc) FROM pc1 a;
將一個表的統計結果插入另一個表中
hive> FROM invites a INSERT OVERWRITE TABLE events SELECT a.bar, count(1) WHERE a.foo > 0 GROUP BY a.bar;
hive> INSERT OVERWRITE TABLE events SELECT a.bar, count(1) FROM invites a WHERE a.foo > 0 GROUP BY a.bar;
JOIN
hive> FROM pokes t1 JOIN invites t2 ON (t1.bar = t2.bar) INSERT OVERWRITE TABLE events SELECT t1.bar, t1.foo, t2.foo;
將多表數據插入到同一表中
FROM src
INSERT OVERWRITE TABLE dest1 SELECT src.* WHERE src.key < 100
INSERT OVERWRITE TABLE dest2 SELECT src.key, src.value WHERE src.key >= 100 and src.key < 200
INSERT OVERWRITE TABLE dest3 PARTITION(ds='2008-04-08', hr='12') SELECT src.key WHERE src.key >= 200 and src.key < 300
INSERT OVERWRITE LOCAL DIRECTORY '/tmp/dest4.out' SELECT src.value WHERE src.key >= 300;
將文件流直接插入文件
hive> FROM invites a INSERT OVERWRITE TABLE events SELECT TRANSFORM(a.foo, a.bar) AS (oof, rab) USING '/bin/cat' WHERE a.ds > '2008-08-09';
This streams the data in the map phase through the script /bin/cat (like hadoop streaming). Similarly - streaming can be used on the reduce side (please see the Hive Tutorial or examples)
實際示例
創建一個表
CREATE TABLE u_data (
userid INT,
movieid INT,
rating INT,
unixtime STRING)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '\t'
STORED AS TEXTFILE;
下載示例數據文件，並解壓縮
wget http://www.grouplens.org/system/files/ml-data.tar__0.gz
tar xvzf ml-data.tar__0.gz
加載數據到表中
LOAD DATA LOCAL INPATH 'ml-data/u.data'
OVERWRITE INTO TABLE u_data;
統計數據總量
SELECT COUNT(1) FROM u_data;
現在做一些複雜的數據分析
創建一個 weekday_mapper.py: 文件，作爲數據按周進行分割
import sys
import datetime

for line in sys.stdin:
line = line.strip()
userid, movieid, rating, unixtime = line.split('\t')
生成數據的周信息
weekday = datetime.datetime.fromtimestamp(float(unixtime)).isoweekday()
print '\t'.join([userid, movieid, rating, str(weekday)])
使用映射腳本
//創建表，按分割符分割行中的字段值
CREATE TABLE u_data_new (
userid INT,
movieid INT,
rating INT,
weekday INT)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '\t';
//將python文件加載到系統
add FILE weekday_mapper.py;
將數據按周進行分割
INSERT OVERWRITE TABLE u_data_new
SELECT
TRANSFORM (userid, movieid, rating, unixtime)
USING 'python weekday_mapper.py'
AS (userid, movieid, rating, weekday)
FROM u_data;

SELECT weekday, COUNT(1)
FROM u_data_new
GROUP BY weekday;
處理Apache Weblog 數據
將WEB日誌先用正則表達式進行組合，再按需要的條件進行組合輸入到表中
add jar ../build/contrib/hive_contrib.jar;

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.contrib.serde2.RegexSerDe'
WITH SERDEPROPERTIES (
"input.regex" = "([^ ]*) ([^ ]*) ([^ ]*) (-|\\[[^\\]]*\\]) ([^ \"]*|\"[^\"]*\") (-|[0-9]*) (-|[0-9]*)(?: ([^ \"]*|\"[^\"]*\") ([^ \"]*|\"[^\"]*\"))?",
"output.format.string" = "%1$s %2$s %3$s %4$s %5$s %6$s %7$s %8$s %9$s"
)
STORED AS TEXTFILE;