【总结】各种数据格式的Hive建表语句-创新互联

Xml格式

CREATE EXTERNAL TABLE Gateway_pmsarisoap(

轮台网站建设公司成都创新互联,轮台网站设计制作，有大型网站制作公司丰富经验。已为轮台上千余家提供企业网站建设服务。企业网站搭建\成都外贸网站制作要多少钱，请找那个售后服务好的轮台做网站的公司定做！

BookingSoapLogID STRING,

GuidNo STRING,

SoapType STRING,

SoapContent STRING,

InsertDate STRING,

SourceOpsType STRING)

PARTITIONED BY (

 `dt` string)

ROW FORMAT SERDE 'com.ibm.spss.hive.serde2.xml.XmlSerDe'

WITH SERDEPROPERTIES (

"column.xpath.BookingSoapLogID"="/HWSoapBase/BookingSoapLogID/text()",

"column.xpath.GuidNo"="/HWSoapBase/GuidNo/text()",

"column.xpath.SoapType"="/HWSoapBase/SoapType/text()",

"column.xpath.SoapContent"="/HWSoapBase/SoapContent/*",

"column.xpath.InsertDate"="/HWSoapBase/InsertDate/text()",

"column.xpath.SourceOpsType"="/HWSoapBase/SourceOpsType/text()"

)

STORED AS

INPUTFORMAT 'com.ibm.spss.hive.serde2.xml.XmlInputFormat'

OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat'

LOCATION 'hdfs://ns1/wh/source/hw/Gateway/PmsARISoap'

TBLPROPERTIES (

"xmlinput.start"="

"xmlinput.end"=""

);

Json格式

CREATE EXTERNAL TABLE QuhuhuGateway_pmsinvcountnotify(

CountType string,

Count string,

HotelCode string,

Start string,

`End` string)

PARTITIONED BY (dt string)

ROW FORMAT SERDE 'com.cloudera.hive.serde.JSONSerDe'

STORED AS INPUTFORMAT 'com.hadoop.mapred.DeprecatedLzoTextInputFormat'

OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'

LOCATION 'hdfs://ns1/wh/source/hw/QuhuhuGateway/PmsInvCountNotify';

ORC格式

create external table BWAdmin_Log(

 `LogID` BIGINT,

 `AccountID` BIGINT,

 `VHotelID` BIGINT,

 `LogType` String,

 `LogComment` String,

 `OperateTime` INT

)

row format delimited

fields terminated by '\t'

STORED AS ORC

location

'hdfs://ns1/wh/source/bw/hotel/admin_log'

AVRO格式

CREATE EXTERNAL TABLE `hotel_list`

PARTITIONED BY ( `dt` string)

ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'

WITH SERDEPROPERTIES( 'avro.schema.url'='hdfs://ns1/wh/config/schema/web/online/hotel_list.avsc')

STORED AS INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'

OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'

LOCATION 'hdfs://ns1/wh/format/online_search';

LZO格式

CREATE EXTERNAL TABLE online_test(

sid int,

pvid int,

ts bigint)

PARTITIONED BY ( dt string)

ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'

LINES TERMINATED BY '\n'

STORED AS INPUTFORMAT'com.hadoop.mapred.DeprecatedLzoTextInputFormat'

OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'

LOCATION 'hdfs://ns1/test/online';

TEXT格式

CREATE EXTERNAL TABLE `order_currenthis`(

`orderid` string,

`room` int)

PARTITIONED BY ( `dt` string)

ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n'

STORED AS INPUTFORMAT 'org.apache.hadoop.mapred.TextInputFormat'

OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'

LOCATION 'hdfs://ns1/wh/format/otb/order_currenthis'

另外有需要云服务器可以了解下创新互联scvps.cn，海内外云服务器15元起步，三天无理由+7*72小时售后在线，公司持有idc许可证，提供“云服务器、裸金属服务器、高防服务器、香港服务器、美国服务器、虚拟主机、免备案服务器”等云主机租用服务以及企业上云的综合解决方案，具有“安全稳定、简单易用、服务可用性高、性价比高”等特点与优势，专为企业上云打造定制，能够满足用户丰富、多元化的应用场景需求。