PREHOOK: query: EXPLAIN CREATE TABLE serde_regex( host STRING, identity STRING, user STRING, time STRING, request STRING, status STRING, size INT, referer STRING, agent STRING) ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe' WITH SERDEPROPERTIES ( "input.regex" = "([^ ]*) ([^ ]*) ([^ ]*) (-|\\[[^\\]]*\\]) ([^ \"]*|\"[^\"]*\") (-|[0-9]*) (-|[0-9]*)(?: ([^ \"]*|\"[^\"]*\") ([^ \"]*|\"[^\"]*\"))?" ) STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: EXPLAIN CREATE TABLE serde_regex( host STRING, identity STRING, user STRING, time STRING, request STRING, status STRING, size INT, referer STRING, agent STRING) ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe' WITH SERDEPROPERTIES ( "input.regex" = "([^ ]*) ([^ ]*) ([^ ]*) (-|\\[[^\\]]*\\]) ([^ \"]*|\"[^\"]*\") (-|[0-9]*) (-|[0-9]*)(?: ([^ \"]*|\"[^\"]*\") ([^ \"]*|\"[^\"]*\"))?" ) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE ABSTRACT SYNTAX TREE: (TOK_CREATETABLE (TOK_TABNAME serde_regex) TOK_LIKETABLE (TOK_TABCOLLIST (TOK_TABCOL host TOK_STRING) (TOK_TABCOL identity TOK_STRING) (TOK_TABCOL user TOK_STRING) (TOK_TABCOL time TOK_STRING) (TOK_TABCOL request TOK_STRING) (TOK_TABCOL status TOK_STRING) (TOK_TABCOL size TOK_INT) (TOK_TABCOL referer TOK_STRING) (TOK_TABCOL agent TOK_STRING)) (TOK_TABLESERIALIZER (TOK_SERDENAME 'org.apache.hadoop.hive.serde2.RegexSerDe' (TOK_TABLEPROPERTIES (TOK_TABLEPROPLIST (TOK_TABLEPROPERTY "input.regex" "([^ ]*) ([^ ]*) ([^ ]*) (-|\\[[^\\]]*\\]) ([^ \"]*|\"[^\"]*\") (-|[0-9]*) (-|[0-9]*)(?: ([^ \"]*|\"[^\"]*\") ([^ \"]*|\"[^\"]*\"))?"))))) TOK_TBLTEXTFILE) STAGE DEPENDENCIES: Stage-0 is a root stage STAGE PLANS: Stage: Stage-0 Create Table Operator: Create Table columns: host string, identity string, user string, time string, request string, status string, size int, referer string, agent string if not exists: false input format: org.apache.hadoop.mapred.TextInputFormat # buckets: -1 output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat serde name: org.apache.hadoop.hive.serde2.RegexSerDe serde properties: input.regex ([^ ]*) ([^ ]*) ([^ ]*) (-|\[[^\]]*\]) ([^ "]*|"[^"]*") (-|[0-9]*) (-|[0-9]*)(?: ([^ "]*|"[^"]*") ([^ "]*|"[^"]*"))? name: serde_regex isExternal: false PREHOOK: query: CREATE TABLE serde_regex( host STRING, identity STRING, user STRING, time STRING, request STRING, status STRING, size INT, referer STRING, agent STRING) ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe' WITH SERDEPROPERTIES ( "input.regex" = "([^ ]*) ([^ ]*) ([^ ]*) (-|\\[[^\\]]*\\]) ([^ \"]*|\"[^\"]*\") (-|[0-9]*) (-|[0-9]*)(?: ([^ \"]*|\"[^\"]*\") ([^ \"]*|\"[^\"]*\"))?" ) STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE serde_regex( host STRING, identity STRING, user STRING, time STRING, request STRING, status STRING, size INT, referer STRING, agent STRING) ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe' WITH SERDEPROPERTIES ( "input.regex" = "([^ ]*) ([^ ]*) ([^ ]*) (-|\\[[^\\]]*\\]) ([^ \"]*|\"[^\"]*\") (-|[0-9]*) (-|[0-9]*)(?: ([^ \"]*|\"[^\"]*\") ([^ \"]*|\"[^\"]*\"))?" ) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@serde_regex PREHOOK: query: LOAD DATA LOCAL INPATH "../data/files/apache.access.log" INTO TABLE serde_regex PREHOOK: type: LOAD PREHOOK: Output: default@serde_regex POSTHOOK: query: LOAD DATA LOCAL INPATH "../data/files/apache.access.log" INTO TABLE serde_regex POSTHOOK: type: LOAD POSTHOOK: Output: default@serde_regex PREHOOK: query: LOAD DATA LOCAL INPATH "../data/files/apache.access.2.log" INTO TABLE serde_regex PREHOOK: type: LOAD PREHOOK: Output: default@serde_regex POSTHOOK: query: LOAD DATA LOCAL INPATH "../data/files/apache.access.2.log" INTO TABLE serde_regex POSTHOOK: type: LOAD POSTHOOK: Output: default@serde_regex PREHOOK: query: SELECT * FROM serde_regex ORDER BY time PREHOOK: type: QUERY PREHOOK: Input: default@serde_regex #### A masked pattern was here #### POSTHOOK: query: SELECT * FROM serde_regex ORDER BY time POSTHOOK: type: QUERY POSTHOOK: Input: default@serde_regex #### A masked pattern was here #### 127.0.0.1 - frank [10/Oct/2000:13:55:36 -0700] "GET /apache_pb.gif HTTP/1.0" 200 2326 NULL NULL 127.0.0.1 - - [26/May/2009:00:00:00 +0000] "GET /someurl/?track=Blabla(Main) HTTP/1.1" 200 5864 - "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/1.0.154.65 Safari/525.19" PREHOOK: query: SELECT host, size, status, time from serde_regex ORDER BY time PREHOOK: type: QUERY PREHOOK: Input: default@serde_regex #### A masked pattern was here #### POSTHOOK: query: SELECT host, size, status, time from serde_regex ORDER BY time POSTHOOK: type: QUERY POSTHOOK: Input: default@serde_regex #### A masked pattern was here #### 127.0.0.1 2326 200 [10/Oct/2000:13:55:36 -0700] 127.0.0.1 5864 200 [26/May/2009:00:00:00 +0000] PREHOOK: query: DROP TABLE serde_regex PREHOOK: type: DROPTABLE PREHOOK: Input: default@serde_regex PREHOOK: Output: default@serde_regex POSTHOOK: query: DROP TABLE serde_regex POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@serde_regex POSTHOOK: Output: default@serde_regex PREHOOK: query: EXPLAIN CREATE TABLE serde_regex1( key decimal, value int) ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe' WITH SERDEPROPERTIES ( "input.regex" = "([^ ]*) ([^ ]*)" ) STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: EXPLAIN CREATE TABLE serde_regex1( key decimal, value int) ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe' WITH SERDEPROPERTIES ( "input.regex" = "([^ ]*) ([^ ]*)" ) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE ABSTRACT SYNTAX TREE: (TOK_CREATETABLE (TOK_TABNAME serde_regex1) TOK_LIKETABLE (TOK_TABCOLLIST (TOK_TABCOL key TOK_DECIMAL) (TOK_TABCOL value TOK_INT)) (TOK_TABLESERIALIZER (TOK_SERDENAME 'org.apache.hadoop.hive.serde2.RegexSerDe' (TOK_TABLEPROPERTIES (TOK_TABLEPROPLIST (TOK_TABLEPROPERTY "input.regex" "([^ ]*) ([^ ]*)"))))) TOK_TBLTEXTFILE) STAGE DEPENDENCIES: Stage-0 is a root stage STAGE PLANS: Stage: Stage-0 Create Table Operator: Create Table columns: key decimal, value int if not exists: false input format: org.apache.hadoop.mapred.TextInputFormat # buckets: -1 output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat serde name: org.apache.hadoop.hive.serde2.RegexSerDe serde properties: input.regex ([^ ]*) ([^ ]*) name: serde_regex1 isExternal: false PREHOOK: query: CREATE TABLE serde_regex1( key decimal, value int) ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe' WITH SERDEPROPERTIES ( "input.regex" = "([^ ]*) ([^ ]*)" ) STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE serde_regex1( key decimal, value int) ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe' WITH SERDEPROPERTIES ( "input.regex" = "([^ ]*) ([^ ]*)" ) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@serde_regex1 PREHOOK: query: LOAD DATA LOCAL INPATH "../data/files/kv7.txt" INTO TABLE serde_regex1 PREHOOK: type: LOAD PREHOOK: Output: default@serde_regex1 POSTHOOK: query: LOAD DATA LOCAL INPATH "../data/files/kv7.txt" INTO TABLE serde_regex1 POSTHOOK: type: LOAD POSTHOOK: Output: default@serde_regex1 PREHOOK: query: SELECT key, value FROM serde_regex1 ORDER BY key, value PREHOOK: type: QUERY PREHOOK: Input: default@serde_regex1 #### A masked pattern was here #### POSTHOOK: query: SELECT key, value FROM serde_regex1 ORDER BY key, value POSTHOOK: type: QUERY POSTHOOK: Input: default@serde_regex1 #### A masked pattern was here #### NULL 0 NULL 0 -1234567890.123456789 -1234567890 -4400 4400 -1255.49 -1255 -1.122 -11 -1.12 -1 -1.12 -1 -0.333 0 -0.33 0 -0.3 0 0 0 0 0 0.01 0 0.02 0 0.1 0 0.2 0 0.3 0 0.33 0 0.333 0 0.9999999999999999999999999 1 1 1 1 1 1.12 1 1.122 1 2 2 2 2 3.14 3 3.14 3 3.14 3 3.14 4 10 10 20 20 100 100 124 124 125.2 125 200 200 1234567890.12345678 1234567890 PREHOOK: query: DROP TABLE serde_regex1 PREHOOK: type: DROPTABLE PREHOOK: Input: default@serde_regex1 PREHOOK: Output: default@serde_regex1 POSTHOOK: query: DROP TABLE serde_regex1 POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@serde_regex1 POSTHOOK: Output: default@serde_regex1