云平台丢失文件的查找办法

-- 测试环境
10.10.14.159
dsideal_db_duibi



-- 创建表
CREATE TABLE  IF NOT EXISTS `aaaa`  (
  `name` varchar(255) CHARACTER SET utf8 COLLATE utf8_general_ci DEFAULT NULL
) ENGINE = InnoDB CHARACTER SET = utf8 COLLATE = utf8_general_ci ROW_FORMAT = Compact;

-- 清空表
truncate table `aaaa`;

-- 创建split函数
CREATE FUNCTION SPLIT_STR(
  x VARCHAR(255),
  delim VARCHAR(12),
  pos INT
)
RETURNS VARCHAR(255)
RETURN REPLACE(SUBSTRING(SUBSTRING_INDEX(x, delim, pos),
       LENGTH(SUBSTRING_INDEX(x, delim, pos -1)) + 1),
       delim, '');


-- 打开Navicat Premium,打开表aaaa,将数据粘贴上去


-- 如果表存在,就删除掉
drop table  if exists t_lost_thumbs;

-- 创建正式表
create table t_lost_thumbs (select split_str(`name`, ' ',1) as id,replace(`name`,concat(split_str(`name`, ' ',1),' ') ,'') as sname,(select substring_index(aaaa.name,'.',-1)) as ext from aaaa);

-- 查看一下
select * from t_lost_thumbs;

-- 按文件名聚合统计一下
select sname,count(*) as scount from t_lost_thumbs GROUP BY sname order by count(*) desc;

-- 按扩展名聚合一下
select ext ,count(*) as scount from t_lost_thumbs group by ext order by count(*) desc;


--===============================================================================
云资源总个数:2414510

丢失缩略图个数:7715


其中swf,mp4,ppt,wmv为主要丢失的类型,需要分别想办法进行丢失文件修复。
swf    5167
mp4    5163
ppt    2695
wmv    570
flv    231
jpg    189
mpg    49
asf    22
png    6
mpeg    3
jpeg    1
gif    1
-- ================================================================================================================

丢失的文件查找:


-- 打开Navicat Premium,打开表aaaa,将数据粘贴上去

-- 如果表存在,就删除掉
drop table  if exists t_lost_files;

-- 创建正式表
create table t_lost_files (select split_str(`name`, ' ',1) as id,replace(`name`,concat(split_str(`name`, ' ',1),' ') ,'') as sname,(select substring_index(aaaa.name,'.',-1)) as ext from aaaa);

-- 查看一下
select * from t_lost_files;

-- 按扩展名聚合一下
select ext ,count(*) as scount from t_lost_files group by ext order by count(*) desc;

================================================================================================================

测试用例 :


http://video.edusoa.com/down/Material/19/1995C8C9-92DC-464B-BD3F-00AF45116CF6.wmv
http://video.edusoa.com/down/Material/7B/7B91BBEB-7553-4359-BACD-2BBBF5988AD1.wmv
http://video.edusoa.com/down/Material/77/77BF13EE-0BDD-B837-21D6-634501372BF9.swf
http://video.edusoa.com/down/Material/28/28A98B04-0ECE-F21E-D147-A5D2573B05CD.swf
http://video.edusoa.com/down/Material/01/01024397-BC36-4111-9B2B-9437F5A8DFEB.ppt
http://video.edusoa.com/down/Material/7C/7CABD07E-EB50-46B1-8953-20A25EB6FD0C.mpg

原文地址:https://www.cnblogs.com/littlehb/p/9000803.html