Untitled

regex for access log in hive serde

66.249.68.6 - - [14/Jan/2012:06:25:03 -0800] "GET /example.com HTTP/1.1" 200 708 "-" "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"

       

CREATE TABLE access_log (

  remote_ip STRING,

  request_date STRING,

  method STRING,

  request STRING,

  protocol STRING

)

ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.RegexSerDe'

WITH SERDEPROPERTIES  (

"input.regex" = "([^ ]) . . [([^]]+)] "([^ ]) ([^ ]) ([^ "])" *",

"output.format.string" = "%1$s %2$s %3$s %4$s %5$s"

)

STORED AS TEXTFILE;

       

"input.regex" = "([0-9]+.[0-9]+.[0-9]+.[0-9]+)[^[]+[([^]]+)][^/]+([^ ]+).+"

"output.format.string" = "%1$s %2$s %3$s"