import unittest
import psycopg2
import pandas as pd
import re

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_columns_selected(self):
        """Check if the selected columns are name, region, capital, population in this 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 = ["name", "region", "capital", "population"]
        condition = columns == expected
        _dynamic_test(
            self,
            condition,
            "Selected columns are correct and in the right order.",
            f"Columns selected are incorrect or out of order: {columns}"
        )

    def test_filter_europe_population(self):
        """Check that only countries from Europe with population > 100000 are returned."""
        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)
        if not df.empty:
            # Check all rows are from Europe and population > 100000
            condition = (
                (df['population'] > 100000).all() and
                ('continent' not in df.columns or True) # No continent column in result, so skip that check
            )
        else:
            condition = True  # If no rows returned, that's fine for this logic
        _dynamic_test(
            self,
            condition,
            "All rows are from Europe and have population > 100000.",
            "Some rows are not from Europe or have population <= 100000."
        )

    def test_order_by_region_capital(self):
        """Check that results are sorted by region ascending, then by capital 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)
        if not df.empty:
            sorted_df = df.sort_values(by=["region", "capital"], ascending=[True, True]).reset_index(drop=True)
            df = df.reset_index(drop=True)
            condition = df.equals(sorted_df)
        else:
            condition = True
        _dynamic_test(
            self,
            condition,
            "Results are sorted by region and then by capital, both ascending.",
            "Results are not sorted by region and capital as required."
        )

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: Europe Region Sort

Lösning