Test Case Generation | Set 1 (Random Numbers, Arrays and Matrices) The test cases are an extremely important part of any Software/Project Testing Process. Hence this Set will be very important for all aspiring software developers. The following are the programs to generate test cases. Generating Random Numbers C++ #include<bits/stdc++.h> using namespace std; #define RUN 5 #define MAX 10000000 int main() { srand(time(NULL)); for (int i=1; i<=RUN; i++) printf("%d\n", rand() % MAX); return(0); } Java import java.io.*; import java.util.Random; class GeneratingRandomNumbers { static int requiredNumbers = 5; static int lowerBound = 0; static int upperBound = 1000; public static void main (String[] args) throws IOException { Random random = new Random(); for(int i = 0; i < requiredNumbers; i++) { int a = random.nextInt(upperBound - lowerBound) + lowerBound; System.out.println(a); } } } Python3 import random requiredNumbers = 5; lowerBound = 0; upperBound = 1000; if __name__ == '__main__': for i in range(requiredNumbers): a = random.randrange(0, upperBound - lowerBound) + lowerBound; print(a); C# using System; class GeneratingRandomNumbers { static int requiredNumbers = 5; static int lowerBound = 0; static int upperBound = 1000; public static void Main(String[] args) { Random random = new Random(); for(int i = 0; i < requiredNumbers; i++) { int a = random.Next(upperBound - lowerBound) + lowerBound; Console.WriteLine(a); } } } Javascript <script> let requiredNumbers = 5; let lowerBound = 0; let upperBound = 1000; for(let i = 0; i < requiredNumbers; i++) { let a = Math.floor(Math.random() * (upperBound - lowerBound)) + lowerBound; document.write(a+"<br>"); } </script> Generating Random Arrays C++ #include<bits/stdc++.h> using namespace std; #define RUN 5 #define MAX 10000000 #define MAXNUM 100 int main() { srand(time(NULL)); for (int i=1; i<=RUN; i++) { int NUM = 1 + rand() % MAXNUM; printf("%d\n", NUM); for (int j=1; j<=NUM; j++) printf("%d ", rand() % MAX); printf("\n"); } return(0); } Java import java.io.*; import java.util.Random; class GeneratingRandomArrays { static int RUN = 5; static int lowerBound = 0; static int upperBound = 1000; static int minSize = 10; static int maxSize = 20; public static void main (String[] args) throws IOException { Random random = new Random(); for(int i = 0; i < RUN; i++) { int size = random.nextInt(maxSize - minSize) + minSize; int[] array = new int[size]; System.out.println(size); for(int j = 0; j < size; j++) { int a = random.nextInt(upperBound - lowerBound) + lowerBound; System.out.print(a + " "); } System.out.println(); } } } Python3 import random RUN = 5; lowerBound = 0; upperBound = 1000; minSize = 10; maxSize = 20; if __name__ == '__main__': for i in range(RUN): size = random.randrange(0, maxSize - minSize) + minSize; array = [0]*size; print(size); for j in range(size): a = random.randrange(0, upperBound - lowerBound) + lowerBound; print(a, end=" "); print(); C# using System; class GeneratingRandomArrays { static int RUN = 5; static int lowerBound = 0; static int upperBound = 1000; static int minSize = 10; static int maxSize = 20; public static void Main(String[] args) { Random random = new Random(); for(int i = 0; i < RUN; i++) { int size = random.Next(maxSize - minSize) + minSize; int[] array = new int[size]; Console.WriteLine(size); for(int j = 0; j < size; j++) { int a = random.Next(upperBound - lowerBound) + lowerBound; Console.Write(a + " "); } Console.WriteLine(); } } } Javascript <script> let RUN = 5; let lowerBound = 0; let upperBound = 1000; let minSize = 10; let maxSize = 20; for(let i = 0; i < RUN; i++) { let size = Math.floor(Math.random() * (maxSize - minSize)) + minSize; let array = new Array(size); document.write(size+"<br>"); for(let j = 0; j < size; j++) { let a = Math.floor(Math.random() * (upperBound - lowerBound)) + lowerBound; document.write(a + " "); } document.write("<br>"); } </script> Generating Random Matrix C++ #include<bits/stdc++.h> using namespace std; #define R

geeksforgeeks.org

Test Case Generator Generate test cases for Competitive Coding. Visit Project here and download the zip file For more convenience, right click on 'test_case.exe' after extraction. click on pin to start. Now the tool's icon is pinned to your start menu and can be used directly from there which saves the hussle of going inside the dist folder everytime you want to run the tool. To be kept in mind: This is a plug'n'play tool i.e. no installation is required There could be a case when your web browser or windows defender shows a warning regarding security issue or virus detected and in that case, you would either have to pause your antivirus and/or windows defender for the time being before downloading(can be resumed right after downloading completes). If the pc shows a warning similar to this "Operation did not complete because the file contains a virus or unwanted file", it is probably due to an issue with py2exe and pyinstaller which are used to convert the python program into an executable file. It can be overcome by allowing "insatallation from unknown sources" and setting it up as "Ask always" under the privacy settings. About Project This project is a combined application of Object Oriented Programming, Competitive coding and Tkinter toolkit. I got the motivation to develop this project after I begun my competitive programming journey(not a great one yet though but working my way up gradually), there were many times when I saw people(including me and my friends) stuck on trying to struggle in thinking test cases when their program fails the submission, especially the case with beginners and that is the main reason this project is developed. However, it is not advised to directly use this tool everytime without trying and thinking test cases on your own, but treat it like a hint to a problem, you should try to solve the problem first before looking up the hint and if you're unable to get ahead then it is advisable to go for the hint instead of just wasting more time. Treat this tool similarly. Home Page: Click on the desired type of Test Case. Input Screen Enter the constraints here Make sure that none of the constraints is having values more than 107 and T*maximum_value_of_n/m/k <=107 This limit is applied because Outputs are in the form of arrays, and any array having size more than that would completely use up memory of a standard PC and would cause it to hang. This issue is under consideration and would be soon dealt with. Output Screen On the output screen you can use multiple handy features as well like copy, regenerate new test case, change constraints on single click. Pre-requisites: * To use codes apart from first release, 'tkinter' must be installed. Challenges faced: S.N. Issue Solution/proposed Solution Resolved or not 1. Application window appeared different on windows and Linux based system Manually designed the GUI similar to the Linux one 2. PC freezed when input constraints were too big Set lower and upper limit for constraints 3. Working on big input values split the test case in two or more parts and then concatenate them as strings to generate on large constraints OR Use Heap memory 4. Windows defender/Antivirus/Chrome virus check treated the file as malicious and blocked download Used py2exe instead of pyinstaller and uploaded zip of multiple files instead of --onefile 5. Code became Surprisingly long Converted whole program from simple functions and methods to OOPs Journey of Development of this project: I learned Tkinter a whole lot better while building this project compared to when I just learned and copy pasted code from tutorial. Before this project, All I knew about OOPs was its definition, types and example and used them only for exam and interview purpose but with this project I have used them a lot thoroghly now and now undderstand every bit of what I earlier used to mug up. while developing this project I faced an unforeseen issue of working on a very very long code. In the starting phas

dev.to

I have been doing sport programming for a while and still improving day by day. But one thing I have always wondered is that it would be really nice if I could automate the test-case generation process and cross-validation of my program. Definitely it would be a brute force approach as some test cases would be algorithm specific. Doing a google search gives me a nice link on Quora : How do programming contest problem setters make test cases ? and the popular testlib used by problem setters. But isn't this a chicken-egg problem? Assume I generated 1 million input test cases, but what would I check them against? How will I generate the outputs? Because I am still in the process of validating the program... If my script generates the correct outputs as well, then whats the point of writing the program in the first place. I can submit the script itself. Also, its not possible to write 1 million outputs for generated test cases manually. Can anyone please clarify this confusion. I hope i have clarified the problem correctly. asked Dec 28, 2016 at 10:35 NaveenNaveen7,98413 gold badges78 silver badges170 bronze badges It's common to generate the answer by a slow but obviously correct solution (like an exhaustive search). It can't be used as a main solution as it's too slow for large test cases, but you can check the output of your fast (but possibly incorrect) program using it. answered Dec 28, 2016 at 11:30 kraskevichkraskevich18.4k4 gold badges33 silver badges45 bronze badges 2 Well the thing is it is not as broad as you think it to be. Test generation in competitive programming is guided by the algorithm of the problem and it's correctness proof. So when you are thinking that there are million of test cases if you analyze the different situations the program can be then you will likely to get all the test cases. Maybe in certain algorithm you are some times processing the even index elements or the odd index elements of an array. Now what you will do? Divide it in 2 cases even or odd. Consider the smallest case for even ones . Same for odd ones. This way you are basically visiting all the control flow path of the program. In competitive programming as we first determine the algorithm then we decide on a proper input sizes and then all this test cases and validations, it is often easy to think the corner points. Test case for 1000000 elements or when input is 0 or 1 ...test cases like this. Another is most of the time we write a brute force solution much more slower than the original one. Now what we do? we just generate random medium size test cases and then run it again the slow program and we can check with our checker solution etc. correctness is guided by some mathematical proof also.(Heuristics, Induction, Box principle, Number Theory etc ) That way we are sure about the correctness of the solution. answered Dec 28, 2016 at 14:05 user2736738user273673830.7k5 gold badges42 silver badges56 bronze badges 8 I faced the same issue earlier this year and saw some of my colleagues also figuring out a way to deal with this. Because there are sometimes when I just couldnt think any more test cases and thats when I decided to make a test case generator tool of my own, Its free and open-source so anyone can use it. You can easily generate a lot of test cases using this tool and validate the result using the output given from the correct but slower approach(in terms of time complexity and space complexity). You can either run them parallelly and check for outputs or write a simple script to compare the output of both programs (the slower but correct one and the better but unsure one) to validate. I believe good coders wont be needing it anyway, but for the middle level (div2, div3) coders and newbies, it can prove to be a lot helpful. You can access it from GitHub : Test Case generator. Both python source code and .exe files are present there with instructions, If you want to make some changes of your own you can work with the python fil

stackoverflow.com

npmjs.com