blob: a193ef76555a03930507c87994e2a231eb7ae3a7 [file] [log] [blame]
set hive.mapred.mode=nonstrict;
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;
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;
LOAD DATA LOCAL INPATH "../../data/files/apache.access.log" INTO TABLE serde_regex;
LOAD DATA LOCAL INPATH "../../data/files/apache.access.2.log" INTO TABLE serde_regex;
SELECT * FROM serde_regex ORDER BY `time`;
SELECT host, size, status, `time` from serde_regex ORDER BY `time`;
DROP TABLE serde_regex;
EXPLAIN
CREATE TABLE serde_regex1(
key decimal(38,18),
value int)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe'
WITH SERDEPROPERTIES (
"input.regex" = "([^ ]*) ([^ ]*)"
)
STORED AS TEXTFILE;
CREATE TABLE serde_regex1(
key decimal(38,18),
value int)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe'
WITH SERDEPROPERTIES (
"input.regex" = "([^ ]*) ([^ ]*)"
)
STORED AS TEXTFILE;
LOAD DATA LOCAL INPATH "../../data/files/kv7.txt" INTO TABLE serde_regex1;
SELECT key, value FROM serde_regex1 ORDER BY key, value;
DROP TABLE serde_regex1;
EXPLAIN
CREATE TABLE serde_regex2(
key STRING,
value STRING)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe'
WITH SERDEPROPERTIES (
"input.regex" = "([^ ]*),([^ ]*)",
"serialization.encoding" = "ISO8859_1"
)
STORED AS TEXTFILE;
CREATE TABLE serde_regex2(
key STRING,
value STRING)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe'
WITH SERDEPROPERTIES (
"input.regex" = "([^ ]*),([^ ]*)",
"serialization.encoding" = "ISO8859_1"
)
STORED AS TEXTFILE;
LOAD DATA LOCAL INPATH "../../data/files/encoding_iso-8859-1.txt" INTO TABLE serde_regex2;
SELECT key, value FROM serde_regex2 ORDER BY key, value;
DROP TABLE serde_regex2;