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_columns_present(self):
        """Check that all original columns plus masked_name are present in the result."""
        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 = set(["id", "name", "masked_name", "email", "city"])
        _dynamic_test(
            self,
            expected_columns.issubset(set(columns)),
            "All required columns are present in the result.",
            f"Missing columns: {expected_columns - set(columns)}"
        )

    def test_all_customers_included(self):
        """Check that all customers are included in the result."""
        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)
        rows = self.cursor.fetchall()
        _dynamic_test(
            self,
            len(rows) == expected_count,
            "All customers are included in the result.",
            f"Expected {expected_count} customers, got {len(rows)}."
        )

    def test_masked_name_format(self):
        """Check that masked_name is correct: first character + asterisks for the rest."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute("SELECT id, name FROM customers;")
        customer_data = {row[0]: row[1] for row in self.cursor.fetchall()}
        self.cursor.execute(query)
        result = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        idx_id = columns.index("id")
        idx_masked = columns.index("masked_name")
        errors = []
        for row in result:
            cid = row[idx_id]
            name = customer_data[cid]
            masked = row[idx_masked]
            if len(name) < 1:
                expected = ''
            else:
                expected = name[0] + ('*' * (len(name)-1))
            if masked != expected:
                errors.append(f"id={cid}: expected '{expected}', got '{masked}'")
        _dynamic_test(
            self,
            not errors,
            "masked_name column is formatted correctly for all rows.",
            "Incorrect masking in rows:\\n" + "\\n".join(errors)
        )

    def test_only_first_character_visible(self):
        """Check that only the first character from the name is visible in masked_name, rest are asterisks."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute("SELECT id, name FROM customers;")
        customer_data = {row[0]: row[1] for row in self.cursor.fetchall()}
        self.cursor.execute(query)
        result = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        idx_id = columns.index("id")
        idx_masked = columns.index("masked_name")
        errors = []
        for row in result:
            cid = row[idx_id]
            name = customer_data[cid]
            masked = row[idx_masked]
            if len(name) > 1 and not all(c == '*' for c in masked[1:]):
                errors.append(f"id={cid}: masked_name has non-asterisk characters after first letter: {masked}")
        _dynamic_test(
            self,
            not errors,
            "Only the first character is visible in masked_name for all rows.",
            "Non-asterisk characters found after the first letter in:\\n" + "\\n".join(errors)
        )

    def test_asterisk_count(self):
        """Check that the number of asterisks matches the number of characters in the name minus one."""
        with open("query.sql", "r") as file:
            query = file.read()
        self.cursor.execute("SELECT id, name FROM customers;")
        customer_data = {row[0]: row[1] for row in self.cursor.fetchall()}
        self.cursor.execute(query)
        result = self.cursor.fetchall()
        columns = [desc[0] for desc in self.cursor.description]
        idx_id = columns.index("id")
        idx_masked = columns.index("masked_name")
        errors = []
        for row in result:
            cid = row[idx_id]
            name = customer_data[cid]
            masked = row[idx_masked]
            expected_asterisks = max(0, len(name) - 1)
            actual_asterisks = masked.count('*')
            if actual_asterisks != expected_asterisks:
                errors.append(f"id={cid}: expected {expected_asterisks} asterisks, got {actual_asterisks} in '{masked}'")
        _dynamic_test(
            self,
            not errors,
            "Asterisk count in masked_name is correct for all rows.",
            "Incorrect asterisk count in:\\n" + "\\n".join(errors)
        )

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

組み込みSQL関数を活用して、文字列、日付、数値、論理値、NULL、JSONデータを操作する方法を習得します。本コースでは、実践的なアプローチでSQL関数の理解と応用を深め、データのクエリや変換スキルを向上させます。

データベース内のテキストデータを操作および分析するための、SQLの強力な文字列関数を学習します。

SQLの日時関数を習得し、時系列データを効果的に扱う。

SQLの数値関数を使用した計算およびデータ分析の習得。

SQLの論理関数を活用して、クエリのフローを制御し、データに基づいた意思決定を行うことができます。

SQLで特殊な関数を使用してNULL値の扱いを習得します。

SQLでJSONデータを扱うための、クエリおよび操作用の専用関数の学習。

チャレンジ：機密情報のマスキング

解答