1. 程式人生 > >大資料-批量資料處理方式

大資料-批量資料處理方式

1.從oracle到hdfs
sqoop import --connect jdbc:oracle:thin:@192.168.0.111:1521:orcl --username user1 --password 123456 --query 'select parti_id,parti_typ_cd from t00_parti where 1=1 and $CONDITIONS' --split-by parti_id -m 1 --target-dir /user/xb6

2.從hdfs到hive
CREATE EXTERNAL TABLE ds.t00_parti (
parti_id VARCHAR(50) ,
parti_typ_cd VARCHAR(50)

ROW FORMAT DELIMITED
FIELDS TERMINATED BY '\001'
LINES TERMINATED BY '\n'
STORED AS TEXTFILE
LOCATION '/user/xb6/';

3.從hdfs到oracle
sqoop export --direct --connect jdbc:oracle:thin:@192.168.0.111:1521:dev --username test01 --password 123456 --table T00_PARTI --export-dir /user/xb6/part-m-00000