將nginx日誌匯入到hive中的兩種方法
1 在hive中建表
- CREATE TABLE apachelog (ipaddress STRING, identd STRING, user STRING,finishtime STRING,requestline string, returncode INT, size INT,referer string,agent string) ROW FORMAT SERDE 'org.apache.Hadoop.hive.serde2.dynamic_type.DynamicSerDe'WITH SERDEPROPERTIES ('serialization.format'='org.apache.hadoop.hive.serde2.thrift.TCTLSeparatedProtocol','quote.delim'='("|\\[|\\])','field.delim'=' ','serialization.null.format'='-')STORED AS TEXTFILE;
匯入後日誌格式為
203.208.60.91 - - 05/May/2011:01:18:47 +0800 GET /robots.txt HTTP/1.1 404 1238 Mozilla/5.0
此方法支援hive中函數parse_url(referer,"HOST")
第二種方法匯入
注意:這個方法在建表後,使用查詢語句等前要先執行
hive> add jar /home/hjl/hive/lib/hive_contrib.jar;
或者設定hive/conf/hive-default.conf 添加
<property>
<name>hive.aux.jars.path</name>
<value>file:///usr/local/hadoop/hive/lib/hive-contrib-0.7.0-cdh3u0.jar</value>
</property>
儲存配置
- CREATE TABLE apilog20110505 (ipaddress STRING,identity STRING,user STRING,time STRING,request STRING,protocol STRING,status STRING,size STRING,referer STRING,agent STRING) ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.RegexSerDe' WITH SERDEPROPERTIES ("input.regex" = "([^ ]*) ([^ ]*) ([^ ]*) (-|\\[[^\\]]*\\]) ([^ \"]*|\"[^\"]*) ([^ ]*\") (-|[0-9]*) (-|[0-9]*)(?: ([^ \"]*|\".*\") ([^ \"]*|\".*\"))?","output.format.string" = "%1$s %2$s %3$s %4$s %5$s %6$s %7$s %8$s %9$s %10$s")STORED AS TEXTFILE;
203.208.60.91 - - [05/May/2011:01:18:47 +0800] "GET /robots.txt HTTP/1.1" 404 1238 "-" "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"
此方法中的欄位類型string from deserializer 經測試不支援parse_url(referer,"HOST")擷取網域名稱
可以用select split(referer,"/")[2] from apilog 擷取網域名稱
如果檔案資料是純文字,可以使用 STORED AS TEXTFILE。如果資料需要壓縮,使用 STORED AS SEQUENCE 。
匯入日誌命令
hive>load data local inpath '/home/log/map.gz' overwrite into table log;
匯入日誌支援.gz等格式
匯入日誌後進行分析 例句
統計行數
select count(*) from nginxlog;
統計IP數
select count(DISTINCT ip) from nginxlog;
排行
select t2.ip,t2.xx from (SELECT ip, COUNT(*) AS xx FROM nginxlog GROUP by ip) t2 sort by t2.xx desc
hive>SELECT * from apachelog WHERE ipaddress = '216.211.123.184';
hive> SELECT ipaddress, COUNT(1) AS numrequest FROM apachelog GROUP BY ipaddress SORT BY numrequest DESC LIMIT 1;
hive> set mapred.reduce.tasks=2;
hive> SELECT ipaddress, COUNT(1) AS numrequest FROM apachelog GROUP BY ipaddress SORT BY numrequest DESC LIMIT 1;
hive>CREATE TABLE ipsummary (ipaddress STRING, numrequest INT);
hive>INSERT OVERWRITE TABLE ipsummary SELECT ipaddress, COUNT(1) FROM apachelog GROUP BY ipaddress;
hive>SELECT ipsummary.ipaddress, ipsummary.numrequest FROM (SELECT MAX(numrequest) AS themax FROM ipsummary) ipsummarymax JOIN ipsummary ON ipsummarymax.themax = ipsummary.numrequest;
hive查詢結果匯出為csv的方法(未測試)
hive> set hive.io.output.fileformat=CSVTextFile;
hive> insert overwrite local directory '/tmp/CSVrepos/' select * from S where ... ;