Athena/Glue—解析简单的JSON(但将其视为CSV)

根据我以前的经验 question 我仍然感到震惊,因为这不是有效的JSON,因为它周围没有方括号。

{"firstName": "Neal",    "lastName": "Walters", "city": "Irving", "state", "TX"  }
{"firstName": "Fred",    "lastName": "Flintstone",   "city": "Bedrock",  "state", "TX"}
{"firstName": "Barney",  "lastName": "Rubble",   "city": "Stillwater",   "state", "OK"}

在运行完GLUE之后,这是我的第一个查询,非常令人失望。

CREATE EXTERNAL TABLE `flattb_testflatjson`(
  `col0` string, 
  `col1` string, 
  `col2` string, 
  `col3` string, 
  `col4` string)
ROW FORMAT DELIMITED 
  FIELDS TERMINATED BY ',' 
STORED AS INPUTFORMAT 
  'org.apache.hadoop.mapred.TextInputFormat' 
OUTPUTFORMAT 
  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
LOCATION
  's3://relatix/polygonData/history/testflatjson/'
TBLPROPERTIES (
  'CrawlerSchemaDeserializerVersion'='1.0', 
  'CrawlerSchemaSerializerVersion'='1.0', 
  'UPDATED_BY_CRAWLER'='FlatJsonTestForAthena', 
  'areColumnsQuoted'='false', 
  'averageRecordSize'='83', 
  'classification'='csv', 
  'columnsOrdered'='true', 
  'compressionType'='none', 
  'delimiter'=',', 
  'objectCount'='1', 
  'recordCount'='3', 
  'sizeKey'='255', 
  'typeOfData'='file')