CREATE TABLE apachelog (
dates STRING,
times STRING,
types STRING,
info STRING)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe'
WITH SERDEPROPERTIES (
"input.regex" = "(^[0-9|-]{0,}) ([^ ]*) (INFO|ERROR) ([^*]*)$"
)
STORED AS TEXTFILE; 2、日志文件内容
$ vi /opt/apachelog
# 下面是一段hadoop的日志内容
2016-01-23 14:22:04,407 INFO org.apache.hadoop.http.HttpServer2: Jetty bound to port 8480
2016-01-23 14:22:04,407 INFO org.mortbay.log: jetty-6.1.26
2016-01-23 14:22:05,065 INFO org.mortbay.log: Started HttpServer2$SelectChannelConnectorWithSafeStartup@0.0.0.0:8480
2016-01-23 14:22:05,357 INFO org.apache.hadoop.ipc.CallQueueManager: Using callQueue class java.util.concurrent.LinkedBlockingQueue
2016-01-23 14:22:05,428 INFO org.apache.hadoop.ipc.Server: Starting Socket Reader #1 for port 8485
2016-01-23 14:22:05,470 INFO org.apache.hadoop.ipc.Server: IPC Server Responder: starting
2016-01-23 14:22:05,472 INFO org.apache.hadoop.ipc.Server: IPC Server listener on 8485: starting
2016-01-23 16:00:15,525 ERROR org.apache.hadoop.hdfs.qjournal.server.JournalNode: RECEIVED SIGNAL 15: SIGTERM
2016-01-23 16:00:15,531 INFO org.apache.hadoop.hdfs.qjournal.server.JournalNode: SHUTDOWN_MSG: 3、导入本地数据
hive> load data local inpath '/opt/apachelog' overwrite into table apachelog; 4、查看结果
hive> select * from apachelog;
OK
2016-01-23 14:22:04,407 INFO org.apache.hadoop.http.HttpServer2: Jetty bound to port 8480
2016-01-23 14:22:04,407 INFO org.mortbay.log: jetty-6.1.26
2016-01-23 14:22:05,065 INFO org.mortbay.log: Started HttpServer2$SelectChannelConnectorWithSafeStartup@0.0.0.0:8480
2016-01-23 14:22:05,357 INFO org.apache.hadoop.ipc.CallQueueManager: Using callQueue class java.util.concurrent.LinkedBlockingQueue
2016-01-23 14:22:05,428 INFO org.apache.hadoop.ipc.Server: Starting Socket Reader #1 for port 8485
2016-01-23 14:22:05,470 INFO org.apache.hadoop.ipc.Server: IPC Server Responder: starting
2016-01-23 14:22:05,472 INFO org.apache.hadoop.ipc.Server: IPC Server listener on 8485: starting
2016-01-23 16:00:15,525 ERROR org.apache.hadoop.hdfs.qjournal.server.JournalNode: RECEIVED SIGNAL 15: SIGTERM
2016-01-23 16:00:15,531 INFO org.apache.hadoop.hdfs.qjournal.server.JournalNode: SHUTDOWN_MSG:
Time taken: 0.518 seconds, Fetched: 9 row(s)
这种方式在导入数据到Hive中时,是非常方便的。