import unittest
import psycopg2
import pandas as pd

class TestPostgresQuery(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_selects_correct_columns(self):
        """Check if query selects 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 = ["id", "name", "population", "region"]
        condition = columns == expected_columns
        _dynamic_test(
            self,
            condition,
            "Query selects the correct columns in the correct order.",
            f"Query columns are {columns}, but expected {expected_columns}."
        )

    def test_orders_by_region_desc_population_asc(self):
        """Check if query orders by region descending and then by population ascending."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        rows = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        df = pd.DataFrame(rows, columns=columns)
        # Nulls should come last in DESC order for region
        # Create a key for sorting: region DESC (null last), population ASC (null last)
        def region_key(val):
            # Nulls last for DESC
            return (val["region"] is None, val["region"] if val["region"] is None else -ord(val["region"][0]))
        sorted_df = df.copy()
        # For region DESC (null last), then population ASC
        sorted_df["region_sort"] = sorted_df["region"].apply(lambda x: (x is None, x))
        sorted_df["pop_sort"] = sorted_df["population"].apply(lambda x: (x is None, x))
        # Sort using pandas for comparison
        expected_df = df.sort_values(
            by=["region", "population"],
            ascending=[False, True],
            na_position="last"
        ).reset_index(drop=True)
        # Reset index for both
        sorted_df = sorted_df.sort_values(
            by=["region", "population"],
            ascending=[False, True],
            na_position="last"
        ).reset_index(drop=True)
        condition = expected_df[["id","name","population","region"]].equals(sorted_df[["id","name","population","region"]])
        _dynamic_test(
            self,
            condition,
            "Query orders by region descending and population ascending.",
            "Query does not order by region descending and population ascending."
        )

    def test_returns_expected_rows(self):
        """Check if query returns the expected rows and values based on data."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        rows = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        result_df = pd.DataFrame(rows, columns=columns)
        # Build expected result
        self.cursor.execute("""
            SELECT id, name, population, region  
            FROM country 
            ORDER BY region DESC, population;
        """)
        expected_rows = self.cursor.fetchall()
        expected_columns = [desc[0] for desc in self.cursor.description]
        expected_df = pd.DataFrame(expected_rows, columns=expected_columns)
        # Compare all rows and values
        condition = result_df.equals(expected_df)
        _dynamic_test(
            self,
            condition,
            "Query returns the expected rows and values in order.",
            "Query does not return the expected rows and values in order."
        )

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: Find Countries, IDs, Populations, Regions, and Sort Them

Oplossing