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_all_customers_returned(self):
        """Check that all customer rows are returned."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        rows = self.cursor.fetchall()
        condition = len(rows) == 10
        _dynamic_test(
            self,
            condition,
            "All customers are returned.",
            f"Expected 10 rows, got {len(rows)}."
        )

    def test_domain_column_correct(self):
        """Check that the domain column contains only the part after '@' for each row."""
        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)
        domains_expected = ["example.com"] * 10
        condition = result_df['domain'].tolist() == domains_expected
        _dynamic_test(
            self,
            condition,
            "Domain column contains correct values.",
            f"Domain column values are incorrect: {result_df['domain'].tolist()}"
        )

    def test_id_name_email_columns_match(self):
        """Check that id, name, and email columns match input 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)
        expected_data = [
            (1, 'Alice Johnson', 'alice.johnson@example.com'),
            (2, 'Rajesh Kumar', 'rajesh.kumar@example.com'),
            (3, 'Maria Garcia', 'maria.garcia@example.com'),
            (4, 'Chen Wei', 'chen.wei@example.com'),
            (5, 'Fatima Al-Farsi', 'fatima.alfarsi@example.com'),
            (6, 'John Smith', 'john.smith@example.com'),
            (7, 'Sofia Rossi', 'sofia.rossi@example.com'),
            (8, 'Lucas MÃ¼ller', 'lucas.mueller@example.com'),
            (9, 'Emily Brown', 'emily.brown@example.com'),
            (10, 'Takashi Sato', 'takashi.sato@example.com'),
        ]
        actual_data = list(zip(result_df['id'], result_df['name'], result_df['email']))
        condition = actual_data == expected_data
        _dynamic_test(
            self,
            condition,
            "id, name, and email columns match input data.",
            f"Returned id, name, and email columns do not match input data."
        )

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 beginner course focuses on the essential SQL functions used for data cleaning and transformation. Learners will practice handling missing values, formatting and standardizing data, and applying string, date, numeric, logical, and null handling functions to prepare datasets for analysis. The course provides hands-on challenges directly related to the most common data preparation tasks in SQL.

Challenge: Extract Email Domains

解答