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_row_count(self):
        """Check that the query returns one row for each customer."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute("SELECT COUNT(*) FROM customers;")
        expected_count = self.cursor.fetchone()[0]
        self.cursor.execute(query)
        result = self.cursor.fetchall()
        _dynamic_test(
            self,
            len(result) == expected_count,
            f"Query returns {expected_count} rows as expected.",
            f"Query should return {expected_count} rows, but returned {len(result)}."
        )

    def test_uppercase_and_length(self):
        """Check that the uppercase_name and name_length columns are correct for each customer."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute("SELECT name FROM customers;")
        customer_names = [r[0] for r in self.cursor.fetchall()]
        self.cursor.execute(query)
        rows = self.cursor.fetchall()
        for i, name in enumerate(customer_names):
            if i >= len(rows):
                _dynamic_test(
                    self,
                    False,
                    "",
                    f"Missing row for customer: {name}"
                )
                continue
            uppercase_name, name_length = rows[i]
            expected_upper = name.upper()
            expected_length = len(name)
            cond_upper = uppercase_name == expected_upper
            cond_length = name_length == expected_length
            _dynamic_test(
                self,
                cond_upper,
                f"Uppercase name is correct for '{name}'.",
                f"Uppercase name incorrect for '{name}': expected '{expected_upper}', got '{uppercase_name}'."
            )
            _dynamic_test(
                self,
                cond_length,
                f"Name length is correct for '{name}'.",
                f"Length incorrect for '{name}': expected {expected_length}, got {name_length}."
            )

    def test_column_names(self):
        """Check that the column names are 'uppercase_name' and 'name_length'."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute(query)
        columns = [desc[0] for desc in self.cursor.description]
        cond = (normalize_text(columns[0]) == "uppercase_name" and normalize_text(columns[1]) == "name_length")
        _dynamic_test(
            self,
            cond,
            "Column names are correct.",
            f"Column names should be 'uppercase_name' and 'name_length', but got {columns}."
        )

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: Standardize Customer Names

解答