import unittest
import psycopg2
import pandas as pd

class TestTask(unittest.TestCase):
    @classmethod
    def setUpClass(cls):
        cls.connection = psycopg2.connect(
            host="localhost",
            user="agent",
            password="qwerty",
            dbname="testdb",
            sslmode="disable"
        )
        cls.cursor = cls.connection.cursor()

    def test_columns_and_order(self):
        """Test that the query returns the correct columns in the correct order."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        columns = [desc[0] for desc in self.cursor.description]
        expected_columns = ['name', 'population', 'region', 'capital']
        condition = columns == expected_columns
        _dynamic_test(
            self,
            condition,
            "Query returns columns in correct order: name, population, region, capital.",
            f"Query columns/order incorrect. Got: {columns}, expected: {expected_columns}."
        )

    def test_population_filter(self):
        """Test that only countries with population >= 300000 are returned."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        rows = self.cursor.fetchall()
        population_idx = [desc[0] for desc in self.cursor.description].index('population')
        invalid_rows = [row for row in rows if row[population_idx] is not None and row[population_idx] < 300000]
        condition = len(invalid_rows) == 0
        _dynamic_test(
            self,
            condition,
            "All returned rows have population >= 300000.",
            f"Some rows have population < 300000: {invalid_rows}."
        )

    def test_expected_rows_present(self):
        """Test that all expected countries with population >= 300000 are included in the result."""
        solution_query = """
            SELECT name, population, region, capital 
            FROM country
            WHERE population >= 300000;
        """
        self.cursor.execute(solution_query)
        expected_rows = self.cursor.fetchall()
        with open("query.sql", "r") as file:
            user_query = file.read()
        self.cursor.execute(user_query)
        user_rows = self.cursor.fetchall()
        missing = [row for row in expected_rows if row not in user_rows]
        condition = len(missing) == 0
        _dynamic_test(
            self,
            condition,
            "All expected rows are present in the result.",
            f"Missing expected rows: {missing}."
        )

    def test_no_extra_rows(self):
        """Test that no extra countries (with population < 300000 or NULL) are included in the result."""
        with open("query.sql", "r") as file:
            user_query = file.read()
        self.cursor.execute(user_query)
        user_rows = self.cursor.fetchall()
        solution_query = """
            SELECT name, population, region, capital 
            FROM country
            WHERE population >= 300000;
        """
        self.cursor.execute(solution_query)
        expected_rows = self.cursor.fetchall()
        extra = [row for row in user_rows if row not in expected_rows]
        condition = len(extra) == 0
        _dynamic_test(
            self,
            condition,
            "No extra rows are present in the result.",
            f"Extra rows found: {extra}."
        )

def _dynamic_test(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message
        test_case.assertTrue(True, success_message)
    else:
        test_case._testMethodName = failure_message
        test_case.fail(failure_message)

def normalize_text(text):
    text = text.lower()
    text = re.sub(r"\s{2,}", " ", text)
    text = re.sub(r"\s*([,:?])\s*", r"\1 ", text)
    return text.strip()

if __name__ == "__main__":
    unittest.main()


test_solution.py

Focuses on practical SQL skills for filtering data with WHERE, sorting results with ORDER BY, and summarizing information using GROUP BY and aggregate functions. Hands-on challenges reinforce each concept, preparing learners to analyze and summarize real-world datasets effectively.

Challenge: Population Threshold Query

Solution