CREATE TABLE `rk_test22`(
`index` int,
`country` string,
`description` string,
`designation` string,
`points` int,
`price` int,
`province` string,
`region_1` string,
`region_2` string,
`taster_name` string,
`taster_twitter_handle` string,
`title` string,
`variety` string,
`winery` string)
ROW FORMAT SERDE
'org.apache.hadoop.hive.serde2.OpenCSVSerde'
WITH SERDEPROPERTIES (
'input.regex'=',(?=(?:[^\"]*\"[^\"]*\")*[^\"]*$)')
STORED AS INPUTFORMAT
'org.apache.hadoop.mapred.TextInputFormat'
OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
LOCATION
'hdfs://namever/user/hive/warehouse/robert.db/rk_test22'
TBLPROPERTIES (
'COLUMN_STATS_ACCURATE'='true',
'numFiles'='1',
'skip.header.line.count'='1',
'totalSize'='52796693',
'transient_lastDdlTime'='1516088117');我使用上面的命令创建了配置单元表。现在我想使用loaddata命令将以下行（在csv文件中）加载到表中。LOADDATA命令显示status ok，但我看不到该表中的数据。
0,Italy,"Aromas include tropical fruit, broom, brimstone and dried herb. The palate isn't overly expressive, offering unripened apple, citrus and dried sage alongside brisk acidity.",Vulkà Bianco,87,,Sicily & Sardinia,Etna,,Kerin O’Keefe,@kerinokeefe,Nicosia 2013 Vulkà Bianco (Etna),White Blend,Nicosia
1条答案
按热度按时间oxalkeyp1#
如果您正在加载一行csv文件，则由于以下属性，将跳过该行：
'skip.header.line.count'='1'regex还应该为每列包含一个捕获组。就像这样的回答：https://stackoverflow.com/a/47944328/2700344为什么在ddl表中提供这些设置：
所有这些都应该在ddl和analyze之后自动设置。