Feature/test cases (#89)

* Added custom tsv parser utility

* Feature added Test cases for acceptance testing

* Update CONTRIBUTION Documentation

* Fix type declaration

* Optimised undesired school and center assignment

* skip sus test. move tests to separate module.

---------

Co-authored-by: Samrat Pant <Samrat Pant>
Co-authored-by: sumanashrestha <[email protected]>

Author: samurato

.coveragerc

@@ -0,0 +1,2 @@
+[run]
+omit = app.py, test/utils/*

CONTRIBUTION.md

@@ -23,10 +23,11 @@ Thank you for considering contributing to our project! We welcome contributions
 4. Install dependencies using `pip install -r requirements.txt`
 5. Install pre-commit hook using `pre-commit install`
 6. Run tests using `pytest tests/test_file_name.py ` or specific test name like `pytest tests/test_file_name.py::test_function_name`
-7. Do not push changes without the tests and coverage passing
-8. Commit your changes with **proper** commit messages in imperative form like `Add my best feature`, `Fix issues casusing whatever`, `Update docs` etc: [Good reference here](https://cbea.ms/git-commit/)
-9. Make changes and push to your forked repository
-10. Create PR to the forked repository as mentioned below
+7. Ensure the features is passing the acceptance criteria by `pytest test_results.py ` or `python test_results.py `
+8. Do not push changes without the tests and coverage passing
+9. Commit your changes with **proper** commit messages in imperative form like `Add my best feature`, `Fix issues casusing whatever`, `Update docs` etc: [Good reference here](https://cbea.ms/git-commit/)
+10. Make changes and push to your forked repository
+11. Create PR to the forked repository as mentioned below
 
 
 ### Pull Requests (PRs):

test/__init__.py

@@ -0,0 +1,158 @@
+import unittest
+import sys
+import os
+import subprocess
+import warnings
+
+# Add the parent directory to the Python path
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.utils.custom_tsv_parser import ParseTSVFile
+
+PREF_CUTOFF = -4
+
+
+def get_scode_cscode_id(data):
+    # Create an id with scode and center with sorted values of scode and center
+    school_centers = []
+    for row in data:
+        scode = int(row["scode"])
+        center = int(row["cscode"])
+        sccode_center_id = sorted((scode, center))
+        sccode_center_id = "_".join(map(str, sccode_center_id))
+        school_centers.append(sccode_center_id)
+    return school_centers
+
+
+class TestSchoolCenter(unittest.TestCase):
+    """_Tests to validate the outcome of the output are matching
+    as per the requirements
+
+    Needs the ouptut from the results/school-center.tsv and
+    results/school-center-distance.tsv files to be present
+
+    """
+
+    def setUp(self):
+        self.school_center_file = "results/school-center.tsv"
+        self.school_center_distance_file = "results/school-center-distance.tsv"
+        self.school_center_pref_file = "sample_data/prefs.tsv"
+        schools_tsv = "sample_data/schools_grade12_2081.tsv"
+        centers_tsv = "sample_data/centers_grade12_2081.tsv"
+        cmd = f"python school_center.py {schools_tsv} {centers_tsv} {self.school_center_pref_file}"
+        subprocess.run(cmd, shell=True)
+
+    def tearDown(self):
+        os.remove(self.school_center_file)
+        os.remove(self.school_center_distance_file)
+
+    def test_results_exists(self):
+        """_Test if the application in running which output the results in the
+             results filder_
+
+        Returns:
+            Pass: If the file exists in the results folder
+            Fail: If the file doesnot exists in the results folder
+        """
+        self.assertTrue(os.path.exists(self.school_center_file))
+        self.assertTrue(os.path.exists(self.school_center_distance_file))
+        self.assertTrue(os.path.exists(self.school_center_pref_file))
+
+    def test_scode_student_count_not_more_than_200(self):
+        """_Test if the student count is not more than 200_
+          Test case ID 001:- एक विद्यालयको परिक्षार्थी संख्या हेरी सकभर १००, २०० भन्दा बढी
+                             परीक्षार्थी एकै केन्द्रमा नपर्ने गरी बाँढ्न पर्ने
+
+        Returns:
+            Pass: If the student count is not more than 100
+            Fail: If the student count is more than 100
+        """
+        ptf = ParseTSVFile(self.school_center_file)
+        data = ptf.get_rows()
+        for row in data:
+            student_count = row["allocation"]
+            if int(student_count) > 200:
+                warnings.warn(f"student count is more than 200 for the school {row}")
+
+
+    def test_scode_cscode_not_same(self):
+        """_Test if the output of scode is not equal to cscode_
+          Test case ID :- आफ्नै विद्यालयमा केन्द्र पार्न नहुने
+
+        Returns:
+            Pass: If the scode is not same as cscode
+            Fail: If the scode is same as cscode
+        """
+        scf = ParseTSVFile(self.school_center_file)
+        data = scf.get_rows()
+        failures = []
+        for row in data:
+            scode = row["scode"]
+            cscode = row["cscode"]
+            if scode == cscode:
+                failures.append(f"scode and cscode are same for row {row} {scode}")
+        assert len(failures) == 0, f'{len(failures)} rows failed. {chr(10).join(failures)}'
+
+    def test_no_mutual_centers(self):
+        """_Test if the scode's center is not same as cscode's
+            centre and vice versa_
+          Test case ID :- दुई विद्यालयका परीक्षार्थीको केन्द्र एक अर्कामा पर्न नहुने, अर्थात् कुनै विद्यालयका परीक्षार्थीको केन्द्र परेको विद्यालयका परीक्षार्थीहरूको केन्द्र अघिल्लो विद्यालयमा पार्न नहुने ।
+
+        Returns:
+            Pass: If the scode's center is not same as cscode's center
+            Fail: If the scode's center is same as cscode's center
+        """
+        scf = ParseTSVFile(self.school_center_file)
+        data = scf.get_rows()
+        scodes_centers = []
+
+        scodes_centers = get_scode_cscode_id(data)
+
+        # Check if there are any duplicates id if duplicate then there is a collision between school and center
+        duplicates = [
+            item for item in set(scodes_centers) if scodes_centers.count(item) > 1
+        ]
+
+        self.assertFalse(
+            duplicates,
+            f"Duplicate values found in scode_center_code: {', '.join(duplicates)}",
+        )
+
+    @unittest.skip ("needs review")
+    def test_undesired_cscode_scode_pair(self):
+        """_Test if the schools and the centers are not matched based on the
+        cost preferences defined in the prefs.tsv file_
+          Test case ID :-
+          1 एकै स्वामित्व / व्यवस्थापनको भनी पहिचान भएका केन्द्रमा पार्न नहुने
+          2 विगतमा कुनै विद्यालयको कुनै केन्द्रमा पार्दा समस्या देखिएकोमा केन्द्र दोहोऱ्याउन नहुने
+
+        Returns:
+            Pass: If the schools with undesired scodes are are not paired with its cscodes
+            Fail: If the schools with same management are each other's center
+        """
+
+        scf = ParseTSVFile(self.school_center_file)
+        cpf = ParseTSVFile(self.school_center_pref_file)
+        data_scf = scf.get_rows()
+        data_cpf = cpf.get_rows()
+        for cpf_data in data_cpf:
+            if int(cpf_data["pref"]) < PREF_CUTOFF:
+                data_cpf.remove(cpf_data)
+
+        failures = []
+
+        scodes_centers = get_scode_cscode_id(data_scf)
+
+        undesired_csodes_centers = get_scode_cscode_id(data_cpf)
+        for undesired_cscodes_center in undesired_csodes_centers:
+            if undesired_cscodes_center in scodes_centers:
+                failures.append(
+                    f"Schools with undesired centers {undesired_cscodes_center}"
+                )
+
+        assert len(failures) == 0, f'{len(failures)} rows failed. {chr(10).join(failures)}'
+
+
+
+if __name__ == "__main__":
+    unittest.main()

test/test_results.py

@@ -0,0 +1,50 @@
+import csv
+
+
+class ParseTSVFile:
+    def __init__(self, file_path):
+        self.file_path = file_path
+
+    def read_file(self):
+        with open(self.file_path, "r", newline="", encoding="utf-8") as file:
+            reader = csv.DictReader(file, delimiter="\t")
+            return reader
+
+    def get_columns(self):
+        with open(self.file_path, "r", newline="", encoding="utf-8") as file:
+            reader = csv.DictReader(file, delimiter="\t")
+            return reader.fieldnames
+
+    def get_row_count(self):
+        with open(self.file_path, "r", newline="", encoding="utf-8") as file:
+            reader = csv.DictReader(file, delimiter="\t")
+            return len(list(reader))
+
+    def get_column_count(self):
+        with open(self.file_path, "r", newline="", encoding="utf-8") as file:
+            reader = csv.DictReader(file, delimiter="\t")
+            return len(reader.fieldnames)
+
+    def get_rows(self):
+        with open(self.file_path, "r", newline="", encoding="utf-8") as file:
+            reader = csv.DictReader(file, delimiter="\t")
+            data = []
+            for row in reader:
+                data.append(row)
+            return data
+
+    def get_column_data(self, column_name):
+        with open(self.file_path, "r", newline="", encoding="utf-8") as file:
+            reader = csv.DictReader(file, delimiter="\t")
+            data = []
+            for row in reader:
+                data.append(row[column_name])
+            return data
+
+    def get_row_data(self, row_number):
+        with open(self.file_path, "r", newline="", encoding="utf-8") as file:
+            reader = csv.DictReader(file, delimiter="\t")
+            data = []
+            for row in reader:
+                data.append(row)
+            return data[row_number]