|
Guys,
I have a scenario which need your advice on it.
I try to keep it short here.. So not putting whole thing in.
I need to develop a system which require approval to maintain any record.
Below is my DB design
Student Table
- StuId
- StuName
- StuAddress
- RecStatus (Deleted, Active, Pending Add, Pending Edit or Pending Delete)
Approval Table
- AprId
- AprCat (Add Request, Edit Request or Delete Request)
- AprModule (Which table to refer to)
- AprModuleId (Target Record)
- AprStatus (Pending Approval, Approve, Reject)
- AprBy
- AprDT
Approval Detail Table (Handle Edit Request Record)
- AprDId
- AprId
- UpdField (Which Field to update)
- NewValue (New Record)
For Adding record, system will insert the record into the student table and have it update as Pending Add in RecStatus. The Id will then added to Approval table for Approval Request.
For Delete Record, system will update the record as Pending Delete in RecStatus. The StuId will added to approval table for approval request.
For Edit record, system will not change the record in student table. But it added into the Approval Detail table and sit there for approval. If request approved, system will loop thru the approval detail record and update the fields one by one.
This is how I do it,
Was thinking is there any better way to work with this kind of scenario?
If yes, please point me to the right direction.
Thank
CA
|
|
|
|
|
Based on the information provided, I think you already have the best idea so far. Well done!
|
|
|
|
|
|
I disagree with the entire design concept of delaying a change until it is approved, it feels like a nightmare waiting to happen, the first time someone needs an "urgent" change implemented the workflow will be short circuited by the needs of the business to get the job done.
I use a logging system (almost all system rely on logging) make the changes immediately and record the information in a log file, if there is a problem you can trace the perpetrator and reverse the changes if required. This allows the business to do their job quickly and gives you the recovery information when they screw up.
Never underestimate the power of human stupidity
RAH
|
|
|
|
|
Hi, I like your quote "Never underestimate the power of human stupidity".
The concept is requested by the user which what they been practice right now. No matter how urgent the changes is, they need to go thru the approval before getting the changes out for others to use it.
We do have a log system which log all changes and approval in the system. I agree will your suggestion, as the whole process will be very quick and no delay. But this process will be great if all user know that what is a correct record looks like. Most of the user will just use whatever data display in the system to get the job done. And it will be a mess when 'Someone' found out is a wrong data. It will take a lot of money and resources to reserve it(In Business).
For us, no record is better than wrong record.
Thank for the sharing. 
|
|
|
|
|
Ah user requirements, they will drive you nuts at some stage.
I can understand the requirement (I thought the student thing was only an example) I do suggest you put in place as much validation as you can think of to reduce the need for intelligent input. You may end up with only a few critical fields that need autorisation.
Never underestimate the power of human stupidity
RAH
|
|
|
|
|
Ya, they are driving me nuts now..
Yes, the student thing is an example but the process is not.
Will try to think off any other validation required like what you mention.
Thank for the suggestion.
|
|
|
|
|
Cee Ann wrote: Was thinking is there any better way to work with this kind of scenario?
Ehr.. how does a multi-table update look like (in a transaction please) with someone "approving" each record before it's edited? And what are you going to do with concurrent edits?
Say both I and your boss edit the same record. Now both edits are awaiting approval. And both of us need the ID that's generated, so we can enlist the student into a class. Whose edit will win? It better be my edit 
Whoever felt the need to give his permission; keep him away from the database-design. There's a GOOD reason why a developer creates the design, and not the user. His permission might be required for a business-rule, but it has nothing to do with how we physically store data.
Aw, and why are you prefixing your fieldnames? And why is it already inconsistent? Wouldn't it be a bit more readable if you omit the prefix?
Bastard Programmer from Hell 
If you can't read my code, try converting it here[^]
|
|
|
|
|
Hi,
For multiple table update, are you referring to other table such as classes or course?
On concurrent edit, we only allow record in active status to be edit. If the record is in Pending Edit Approval Status, the record will not be allow to edit again. Until the pending request is approved/rejected. This is been taken care in the RecStatus field of each table.
So, it will not happen that you and my boss edit the same record in same time.
But If it really happen, I will let me boss win. As he is paying my salary.
The database is design by me. If you see any issue with it, please point it out. So I can learn from my mistake.
Forgive my laziness on the prefixing of fieldname, It all started when I writing my SQL statement and felt it's too long.. So I try to shorten it a little bit.
Was learning my way to not prefixing my fieldname with EF6, as I get the suggestion function in VS.
Thanks for the update.
CA
|
|
|
|
|
Cee Ann wrote: For multiple table update, are you referring to other table such as classes or course?
I don't have the entire schema so I can't say to which tables it applies. Let's take a fictive person called Jane and enlist her into three courses. That's 4 items that need be "approved".
Now enlist 400 students in 40 different courses
Cee Ann wrote: If you see any issue with it, please point it out
Whether it is valid depends on the users' needs; I can't tell whether it's valid, but one can always apply the normalization principles. To me it'd be valid if it is in BNF.
Cee Ann wrote: Forgive my laziness on the prefixing of fieldname
Lazy? I was wondering why you're doing all that work, when it doesn't seem to help much
Bastard Programmer from Hell
If you can't read my code, try converting it here[^]
|
|
|
|
|
Eddy Vluggen wrote: Now enlist 400 students in 40 different courses
It will be a lot of approval need to be done.
Luckily I'm the developer not the person who need to approve it.
Eddy Vluggen wrote: To me it'd be valid if it is in BNF.
BNF?
Eddy Vluggen wrote: it doesn't seem to help much
So, if is for you, you will do it as below?
Student Table
- StudentId
- StudentCode
- StudentName
- StudentAddress
- RecordStatus
|
|
|
|
|
Cee Ann wrote: Luckily I'm the developer not the person who need to approve it
Make sure to add in an extra dialog, asking the user whether he/she is sure about the edit and wants to save 
Cee Ann wrote: BNF?
Sorry, BCNF[^]; the normal forms are numbered. The model is said to be in 3NF if you validated the first three rules. BCNF is "rule 3.5", it's somewhere between 3 and 4.
Cee Ann wrote: So, if is for you, you will do it as below?
I'd drop the word "Student" from the fieldname, as there would not be any other entities with an Id in the Student-table. If you're referring to a name in the student-table, then "name" would probably apply to the student. Then I'd rename "RecordStatus" to "ApprovedByFool", as it is more descriptive.
Bastard Programmer from Hell
If you can't read my code, try converting it here[^]
|
|
|
|
|
Go on Eddy - why don't you tell them how you really feel
Everyone dies - but not everyone lives
|
|
|
|
|
Eddy Vluggen wrote: Make sure to add in an extra dialog, asking the user whether he/she is sure about the edit and wants to save
Got it.
BCNF... Something new for me to study..
Eddy Vluggen wrote: I'd drop the word "Student" from the fieldname, as there would not be any other entities with an Id in the Student-table. If you're referring to a name in the student-table, then "name" would probably apply to the student. Then I'd rename "RecordStatus" to "ApprovedByFool", as it is more descriptive.
What if StudentId is a foreign key to other table? Write 'StudentId' as fieldname in the other tables and 'Id' as fieldname in Student table?
|
|
|
|
|
Cee Ann wrote: What if StudentId is a foreign key to other table
Then you could name it after the table it comes from, but it'd be better to come up with a descriptive name. Take "Employee" and "Person" as a fictive example with multiple references to itself;
Employee
Id
Name
FK_Manager
FK_DedicatedDriver
Person
Id
FK_Mother
FK_Father
As you can see, there's no mention of the fact in the fieldname to the table. That's because we can assume that people will recognize "mother" as a person, and "manager" as an employee. If it weren't, "FK_MotherPerson" might be needed.
Cee Ann wrote: Write 'StudentId' as fieldname in the other tables
It's not an id, but a foreign key; it's something that points to the id of a record in a different table
That information is also obvious from the above naming; anything with a "FK" points to the Id-field of another table.
Bastard Programmer from Hell
If you can't read my code, try converting it here[^]
|
|
|
|
|
Got it,
Thanks a lot Eddy for everything.
|
|
|
|
|
You're welcome
|
|
|
|
|
Howdy,
I've a program that receives GPS through a serial port. The GPS class is child to the main form. When the user calls to open the port, the GPS class creates a thread and runs it, firing off a dataReceived event to the main form, the eventArgs class contains the location data and can be read by main form. This program runs constantly for up to a week at a time and interacts with user input the whole time. Usually, once or twice in a week, the program coughs up an error that can freeze the laptop, but at the very least requires a program restart. Because it happens so seldom, I cannot track this sneaky jerk down.
The enventArg data is stored writ to a listArray, which can be polled by the user to get locations at appropriate times for their task. When requested, the form posts a median location, empties the listArray and waits until the array is full again before the user can make their next request.
If the event fires at the same time as a user request, would this cause a problem? If so, how should I approach a fix?
Should I run the GPS class on a thread from the main form?
When a connection to the GPS is closed, should I kill the thread that the dataStream came in on? The stream is disposed of, but I never put closed parenthesis on the thread itself.
public void GpsOpen()
{
if (_gpsStatus.Equals(GpsStatus.Disconnected) || _gpsStatus.Equals(GpsStatus.NoGpsDetected))
{
_gpsStatus = GpsStatus.Connecting;
FireStatusChangedEvent(_gpsStatus);
ThreadStart ts = new ThreadStart(openGps);
gpsThread = new Thread(ts);
gpsThread.Start();
}
}
Suggestions are definitely appreciated!
TnM
If you're not sure you're in a cult, you are.
-- Stephen Colbert
|
|
|
|
|
Random thoughts.
If a thread throws an exception which isn't caught then the entire C# application terminates.
If you are not in fact creating one thread but are creating many then I would suspect the entire OS to fail.
Get a logging library and use it.
|
|
|
|
|
Does the event viewer show any information for that application hang? Well, it hardly ever useful, but might be better than no information at all.
A tight logging of all program calls is preferred.
By the way, are some kind of system events happening at that moment, e.g. hibernate, USB power off, ...
|
|
|
|
|
Unfortunately, this happens in the middle of the ocean and we're on the clock and have to keep going, so it's restart with some random cursing and get back at it. I brought my development machine out once and ran the program through the VS debugger, but the break was not helpful at all. Definitely not a power off or hibernate, that stuff is all turned off, it might be USB, but there are three other peripherals running through the application on their own threads and have never had a problem. Of course, the other three are also not constantly streaming.
Back at sea in a few weeks, I'll definitely check the event log...as you said, w/out much hope! Not sure I've ever gotten any help there.
Don't have much time to spend on this, thought I'd throw this out there and see what came back.
Thanks for your feedback,
TnM
If you're not sure you're in a cult, you are.
-- Stephen Colbert
|
|
|
|
|
I'm looking to build a desktop application which primarily is used for data entry. However, the application needs to have a few features that assist the user in selecting the appropriate data. If you have experience designing applications and have good models/ frameworks that you think would be best after reading this, please let me know. Here are many of the details.
The application idea is to create a UI with one page that has a host of listboxes, comboboxes, textboxes, and tabcontrols. The user will select the data from the combination of controls, then press CREATE RECORDS somewhere in the application. The data that is entered is either going to be entered directly into a database ( postgresql) or will begin in a datagrid and then after review of the records ( perhaps a separate tabitem) , will be placed into the database. The best part about this application would be the speed at which it is able to build records based on looping through the controls. Many of the records that are currently being created have data that is easily created by looping through controls such as listboxes as the data on the records is only different by a slight change in the value that can be shown in a listbox and selected with a multiselect.
I would like to separate the application into its parts as this seems to be common practice for application design and efficiency gains when coding. ( MVVM is just one I have read about recently.) I am going to be using NPGSQL as a data adapter and the rest is simply up for design grabs. If you have any recommendations, please let me know. I would really like to know if there is a better framework to design such an application and have so far been working looking into WPF. All knowledge and recommendations are welcomed. Thank you so much.
|
|
|
|
|
|
Hi Peter, and thank you for the reference material that microsoft wrote. It appears that the article has some relevent information for me, specifically approaches to creating a n-tier application. However, do you feel that this document is slightly outdated considering it was written 12 years ago??
|
|
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
