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_ordering(self):
        """Check that the query extracts 'region' and 'capital' columns ordered by region, then by capital."""
        with open("query.sql", "r") as file:
            query = file.read()

        # Run user query
        self.cursor.execute(query)
        rows = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        result_df = pd.DataFrame(rows, columns=columns)

        # Check columns
        expected_columns = ["region", "capital"]
        has_columns = list(result_df.columns) == expected_columns
        _dynamic_test(
            self,
            has_columns,
            "Query returns only 'region' and 'capital' columns in correct order.",
            f"Query must return only columns 'region' and 'capital' in order. Found: {list(result_df.columns)}"
        )

        # Check ordering
        is_ordered = result_df.equals(result_df.sort_values(["region", "capital"], kind="mergesort").reset_index(drop=True))
        _dynamic_test(
            self,
            is_ordered,
            "Rows are sorted by 'region' then by 'capital'.",
            "Rows are not sorted by 'region' then by 'capital'."
        )

    def test_all_rows_present(self):
        """Check that all expected (region, capital) pairs from the table are present in the output."""
        with open("query.sql", "r") as file:
            query = file.read()

        # Reference query
        sol_query = """
        SELECT region, capital FROM country
        """
        self.cursor.execute(sol_query)
        sol_rows = self.cursor.fetchall()
        sol_columns = [desc[0] for desc in self.cursor.description]
        sol_df = pd.DataFrame(sol_rows, columns=sol_columns)

        self.cursor.execute(query)
        rows = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        result_df = pd.DataFrame(rows, columns=columns)

        # Compare sets of tuples
        expected_set = set(tuple(x) for x in sol_df.values)
        result_set = set(tuple(x) for x in result_df.values)
        missing = expected_set - result_set
        extra = result_set - expected_set
        condition = len(missing) == 0 and len(extra) == 0
        fail_msg = ""
        if missing:
            fail_msg += f"Missing rows: {missing}. "
        if extra:
            fail_msg += f"Unexpected extra rows: {extra}."
        _dynamic_test(
            self,
            condition,
            "All expected (region, capital) pairs are present in the result.",
            fail_msg.strip()
        )

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

This course is perfect for beginners ready to explore the world of SQL. Whether you're just starting out in database management or aiming to use SQL for your application development projects, this course covers the essentials. You'll quickly learn how to leverage the full potential of SQL, from querying and managing data to seamlessly integrating it into real-world applications. By the end of the course, you'll have the confidence and skills to solve practical problems with SQL and enhance your development process.

In this section, we will learn how to use the SQL SELECT statement to get a single table column, multiple table columns, and all table columns. We will also find out how to return unique values.

In this section, we’ll explore how to organize and prioritize the data returned by a query using the ORDER BY clause. Placed at the end of a SELECT statement, this clause lets you sort your results by one or multiple columns, either in ascending or descending order, enabling more meaningful and easily interpretable data output.

In this section, we will learn how to filter returned data using the SELECT statement's WHERE clause. We will learn how to test for equality, inequality, more and less significant than value ranges, and NULL values.

In this section, we’ll explore how to refine your search conditions by combining WHERE clauses with the AND and OR operators. We’ll also cover how the NOT operator can be used to exclude certain results.

In this section, we will learn what the SQL aggregate functions are and how to use them to summarize table data.

Challenge: Dual-Sort Query

Solution