/opt/cloudera/parcels/CDH/lib/sqoop/bin/sqoop import \
--connect jdbc:[mysql://ip:port/T_Cloud_Promote](mysql://ipport) \
--username rt_center \
--password pwd\
--query "select KeywordID,KeyType,Root,KeywordName,UID,Status,AddDate,UpdateDate,MigrateOID,PromotionStatus,WordType,IsEmphasis,KeywordLength,IsViolate,ViolateWord from T_Cloud_Promote.T_Cloud_User_KeywordLibrary where KeywordID < $[a+10000000] AND KeywordID >= ${a} AND AddDate != '0000-00-00 00:00:00' AND \$CONDITIONS" \
--fields-terminated-by '\001' \
--target-dir /tmp/t_cloud_order \
--delete-target-dir \
--hive-import \
--hive-database T_Cloud_Promote \
--hive-table ods_t_cloud_user_keywordlibraryb_tmp_01 \
--null-string '\\N' \
--null-non-string '\\N' \
--hive-drop-import-delims \
--num-mappers 5 \
--split-by KeywordID \
--hive-overwrite
-
–connect
mysql连接 -
–username
用户名 -
–password
密码 -
–query
条件查询语句 -
–fields-terminated-by
分隔符 -
–target-dir
临时存放位置 -
–delete-target-dir \
程序结束删除文件夹 -
–hive-import \
导入到hive -
–hive-database T_Cloud_Promote \
hive的数据库 -
–hive-table
hive表 -
–null-string ‘\N’ \
–null-non-string ‘\N’ \
转换为hive空 -
–hive-drop-import-delims \
删除特殊分隔符如：\n\r \0x01 -
–num-mappers 5 \
指定map的个数 -
–split-by KeywordID \
指定按哪个字段切分 -
–hive-overwrite
覆盖hive表，若不写则追加