Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
L
lmp_server
Project
Project
Details
Activity
Releases
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
lmp
lmp_server
Commits
0634e753
Commit
0634e753
authored
Apr 02, 2024
by
pengxin
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
添加数据清洗功能。
parent
32843a49
Changes
7
Expand all
Hide whitespace changes
Inline
Side-by-side
Showing
7 changed files
with
203 additions
and
122 deletions
+203
-122
DatasetData.java
...src/main/java/com/yice/webadmin/app/data/DatasetData.java
+20
-8
DatasetDataClean.java
...ain/java/com/yice/webadmin/app/data/DatasetDataClean.java
+20
-8
DatasetDataDeduplicate.java
...va/com/yice/webadmin/app/data/DatasetDataDeduplicate.java
+20
-5
DatasetDataDesensitive.java
...va/com/yice/webadmin/app/data/DatasetDataDesensitive.java
+20
-8
DatasetDataFilter.java
...in/java/com/yice/webadmin/app/data/DatasetDataFilter.java
+16
-7
DatasetCleanServiceImpl.java
...ce/webadmin/app/service/impl/DatasetCleanServiceImpl.java
+89
-85
DatasetDataServiceImpl.java
...ice/webadmin/app/service/impl/DatasetDataServiceImpl.java
+18
-1
No files found.
application-webadmin/src/main/java/com/yice/webadmin/app/data/DatasetData.java
View file @
0634e753
package
com
.
yice
.
webadmin
.
app
.
data
;
import
io.swagger.annotations.ApiModel
;
import
io.swagger.annotations.ApiModelProperty
;
import
lombok.AllArgsConstructor
;
import
lombok.Data
;
import
lombok.NoArgsConstructor
;
import
org.springframework.data.annotation.Id
;
import
org.springframework.data.mongodb.core.mapping.Document
;
import
org.springframework.data.mongodb.core.mapping.Field
;
import
java.util.Date
;
@Data
@ApiModel
@NoArgsConstructor
@AllArgsConstructor
@Document
(
collection
=
"dataset_data"
)
public
class
DatasetData
{
/**
* 文档标识
*/
@Id
@ApiModelProperty
(
name
=
"_id"
,
value
=
"文档标识"
)
private
String
id
;
@ApiModelProperty
(
name
=
"version_id"
,
value
=
"版本标识"
)
/**
* 版本标识
*/
@Field
(
"version_id"
)
private
Long
versionId
;
@ApiModelProperty
(
name
=
"data"
,
value
=
"json格式数据"
)
/**
* json格式数据
*/
@Field
(
"data"
)
private
String
data
;
@ApiModelProperty
(
name
=
"create_time"
,
value
=
"创建时间"
)
/**
* 创建时间
*/
@Field
(
"create_time"
)
private
Date
createTime
;
@ApiModelProperty
(
name
=
"mark_status"
,
value
=
"标记状态"
)
/**
* 标记状态
*/
@Field
(
"mark_status"
)
private
Integer
markStatus
;
}
application-webadmin/src/main/java/com/yice/webadmin/app/data/DatasetDataClean.java
View file @
0634e753
package
com
.
yice
.
webadmin
.
app
.
data
;
import
io.swagger.annotations.ApiModel
;
import
io.swagger.annotations.ApiModelProperty
;
import
lombok.AllArgsConstructor
;
import
lombok.Data
;
import
lombok.NoArgsConstructor
;
import
org.springframework.data.annotation.Id
;
import
org.springframework.data.mongodb.core.mapping.Document
;
import
org.springframework.data.mongodb.core.mapping.Field
;
import
java.util.Date
;
@Data
@ApiModel
@NoArgsConstructor
@AllArgsConstructor
@Document
(
collection
=
"dataset_data_clean"
)
public
class
DatasetDataClean
{
/**
* 文档标识
*/
@Id
@ApiModelProperty
(
name
=
"_id"
,
value
=
"文档标识"
)
private
String
id
;
@ApiModelProperty
(
name
=
"clean_id"
,
value
=
"清洗任务标识id"
)
/**
* 清洗任务标识id
*/
@Field
(
"clean_id"
)
private
Long
cleanId
;
@ApiModelProperty
(
name
=
"clean_before_data"
,
value
=
"清洗前数据"
)
/**
* 清洗前数据
*/
@Field
(
"clean_before_data"
)
private
String
cleanBeforeData
;
@ApiModelProperty
(
name
=
"clean_after_data"
,
value
=
"清洗后数据"
)
/**
* 清洗后数据
*/
@Field
(
"clean_after_data"
)
private
String
cleanAfterData
;
@ApiModelProperty
(
name
=
"create_time"
,
value
=
"创建时间"
)
/**
* 创建时间
*/
@Field
(
"create_time"
)
private
Date
createTime
;
}
application-webadmin/src/main/java/com/yice/webadmin/app/data/DatasetDataDeduplicate.java
View file @
0634e753
...
...
@@ -7,6 +7,7 @@ import lombok.Data;
import
lombok.NoArgsConstructor
;
import
org.springframework.data.annotation.Id
;
import
org.springframework.data.mongodb.core.mapping.Document
;
import
org.springframework.data.mongodb.core.mapping.Field
;
import
java.util.Date
;
...
...
@@ -17,19 +18,33 @@ import java.util.Date;
@Document
(
collection
=
"dataset_data_deduplicate"
)
public
class
DatasetDataDeduplicate
{
/**
* 文档标识
*/
@Id
@ApiModelProperty
(
name
=
"_id"
,
value
=
"文档标识"
)
private
String
id
;
@ApiModelProperty
(
name
=
"clean_id"
,
value
=
"清洗任务标识id"
)
/**
* 清洗任务标识id
*/
@Field
(
"clean_id"
)
private
Long
cleanId
;
@ApiModelProperty
(
name
=
"clean_before_data"
,
value
=
"清洗前数据"
)
/**
* 清洗前数据
*/
@Field
(
"clean_before_data"
)
private
String
cleanBeforeData
;
@ApiModelProperty
(
name
=
"clean_after_data"
,
value
=
"清洗后数据"
)
/**
* 清洗后数据
*/
@Field
(
"clean_after_data"
)
private
String
cleanAfterData
;
@ApiModelProperty
(
name
=
"create_time"
,
value
=
"创建时间"
)
/**
* 创建时间
*/
@Field
(
"create_time"
)
private
Date
createTime
;
}
application-webadmin/src/main/java/com/yice/webadmin/app/data/DatasetDataDesensitive.java
View file @
0634e753
package
com
.
yice
.
webadmin
.
app
.
data
;
import
io.swagger.annotations.ApiModel
;
import
io.swagger.annotations.ApiModelProperty
;
import
lombok.AllArgsConstructor
;
import
lombok.Data
;
import
lombok.NoArgsConstructor
;
import
org.springframework.data.annotation.Id
;
import
org.springframework.data.mongodb.core.mapping.Document
;
import
org.springframework.data.mongodb.core.mapping.Field
;
import
java.util.Date
;
@Data
@ApiModel
@NoArgsConstructor
@AllArgsConstructor
@Document
(
collection
=
"dataset_data_desensitive"
)
public
class
DatasetDataDesensitive
{
/**
* 文档标识
*/
@Id
@ApiModelProperty
(
name
=
"_id"
,
value
=
"文档标识"
)
private
String
id
;
@ApiModelProperty
(
name
=
"clean_id"
,
value
=
"清洗任务标识id"
)
/**
* 清洗任务标识id
*/
@Field
(
"clean_id"
)
private
Long
cleanId
;
@ApiModelProperty
(
name
=
"clean_before_data"
,
value
=
"清洗前数据"
)
/**
* 清洗前数据
*/
@Field
(
"clean_before_data"
)
private
String
cleanBeforeData
;
@ApiModelProperty
(
name
=
"clean_after_data"
,
value
=
"清洗后数据"
)
/**
* 清洗后数据
*/
@Field
(
"clean_after_data"
)
private
String
cleanAfterData
;
@ApiModelProperty
(
name
=
"create_time"
,
value
=
"创建时间"
)
/**
* 创建时间
*/
@Field
(
"create_time"
)
private
Date
createTime
;
}
application-webadmin/src/main/java/com/yice/webadmin/app/data/DatasetDataFilter.java
View file @
0634e753
package
com
.
yice
.
webadmin
.
app
.
data
;
import
io.swagger.annotations.ApiModel
;
import
io.swagger.annotations.ApiModelProperty
;
import
lombok.AllArgsConstructor
;
import
lombok.Data
;
import
lombok.NoArgsConstructor
;
import
org.springframework.data.annotation.Id
;
import
org.springframework.data.mongodb.core.mapping.Document
;
import
org.springframework.data.mongodb.core.mapping.Field
;
import
java.util.Date
;
@Data
@ApiModel
@NoArgsConstructor
@AllArgsConstructor
@Document
(
collection
=
"dataset_data_filter"
)
public
class
DatasetDataFilter
{
/**
* 文档标识
*/
@Id
@ApiModelProperty
(
name
=
"_id"
,
value
=
"文档标识"
)
private
String
id
;
@ApiModelProperty
(
name
=
"clean_id"
,
value
=
"清洗任务标识id"
)
/**
* 清洗任务标识id
*/
@Field
(
"clean_id"
)
private
Long
cleanId
;
@ApiModelProperty
(
name
=
"content"
,
value
=
"过滤内容"
)
/**
* 清洗后数据
*/
@Field
(
"content"
)
private
String
content
;
@ApiModelProperty
(
name
=
"create_time"
,
value
=
"创建时间"
)
/**
* 创建时间
*/
@Field
(
"create_time"
)
private
Date
createTime
;
}
application-webadmin/src/main/java/com/yice/webadmin/app/service/impl/DatasetCleanServiceImpl.java
View file @
0634e753
This diff is collapsed.
Click to expand it.
application-webadmin/src/main/java/com/yice/webadmin/app/service/impl/DatasetDataServiceImpl.java
View file @
0634e753
package
com
.
yice
.
webadmin
.
app
.
service
.
impl
;
import
cn.hutool.core.collection.CollUtil
;
import
com.alibaba.fastjson.JSONArray
;
import
com.alibaba.fastjson.JSONObject
;
import
com.yice.common.core.object.MyPageParam
;
...
...
@@ -13,6 +14,7 @@ import org.springframework.beans.factory.annotation.Autowired;
import
org.springframework.data.mongodb.core.MongoTemplate
;
import
org.springframework.data.mongodb.core.query.Criteria
;
import
org.springframework.data.mongodb.core.query.Query
;
import
org.springframework.data.mongodb.core.query.Update
;
import
org.springframework.stereotype.Service
;
import
java.util.ArrayList
;
...
...
@@ -157,7 +159,22 @@ public class DatasetDataServiceImpl implements DatasetDataService {
*/
@Override
public
void
updateBatch
(
List
<
DatasetData
>
dataList
,
Long
versionId
)
{
mongoTemplate
.
save
(
dataList
,
MongoConstant
.
COLLECT_NAME
+
versionId
);
if
(
CollUtil
.
isNotEmpty
(
dataList
))
{
for
(
DatasetData
datasetData
:
dataList
)
{
// 解析data字段的字符串为Document或Bson
Document
dataDocument
=
Document
.
parse
(
datasetData
.
getData
());
// 构建查询条件
Query
query
=
new
Query
(
Criteria
.
where
(
MongoConstant
.
ID
).
is
(
datasetData
.
getId
()));
// 构建更新操作
Update
update
=
new
Update
();
update
.
set
(
MongoConstant
.
DATA
,
dataDocument
);
// 执行更新操作
mongoTemplate
.
updateFirst
(
query
,
update
,
MongoConstant
.
COLLECT_NAME
+
versionId
);
}
}
}
/**
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment