Feature/data validation

README.md

@@ -22,6 +22,8 @@ A modular, pytest-based **Playwright (Python)** framework for web UI testing.
    ```
 
 3. **Bootstrap once (signup → login → save session)**
+   > **Note:** This step is recommended but not required — if `storage_state.json` is missing, pytest will automatically bootstrap the session before running any tests.
+
    ```bash
    python -m scripts.bootstrap_signup --name "Jane Doe" --email "[email protected]" --password "StrongPass123"
    ```
@@ -32,7 +34,7 @@ A modular, pytest-based **Playwright (Python)** framework for web UI testing.
    ```
    > Tip: to **watch it in a real browser**, run headed:
    > ```bash
-   > HEADLESS=false pytest -s tests/test_logged_in_session.py
+   > HEADLESS=false pytest -s tests/test_logged_in.py
    > ```
 
 5. **Run the full suite**

conftest.py

@@ -104,3 +104,16 @@ def page(context):
         yield p
     finally:
         p.close()
+
+# --- Database & Data Validation Lifecycle ---
+
+@pytest.fixture(scope="session")
+def db_engine():
+    """
+    Spawns a mock SQLAlchemy engine structure for backend integration and DataFrame testing.
+    e.g., engine = sqlalchemy.create_engine('sqlite:///:memory:')
+    """
+    # engine = None
+    # yield engine
+    # engine.dispose()
+    yield "mock_engine_connection"

data_clients/db_client.py

@@ -0,0 +1,16 @@
+class DatabaseClient:
+    def __init__(self, engine):
+        self.engine = engine
+
+    def get_user_data(self, user_id):
+        """
+        Skeleton method to return a DataFrame of user data.
+        In reality, this would use pandas.read_sql or SQLAlchemy.
+        """
+        pass
+
+    def get_system_snapshot(self, system_name):
+        """
+        Skeleton method to pull large-scale dataset snapshots.
+        """
+        pass

data_driven_test.py

@@ -0,0 +1,35 @@
+def run_signup_from_csv(csv_path="users.csv", headed=True):
+    import csv
+    from pathlib import Path
+    from playwright.sync_api import sync_playwright, expect
+
+    URL = "https://faruk-hasan.com/automation/signup.html"
+    rows = list(csv.DictReader(Path(csv_path).open(newline="", encoding="utf-8")))
+
+    with sync_playwright() as pw:
+        browser = pw.chromium.launch(headless=not headed)
+        context = browser.new_context()
+
+        for u in rows:
+            page = context.new_page()
+            try:
+                page.goto(URL, wait_until="domcontentloaded")
+                expect(page).to_have_title("Sign Up - Automation Practice")
+
+                page.locator("#username").fill(u["name"].strip())
+                page.locator("#email").fill(u["email"].strip())
+                page.locator("#password").fill(u["password"].strip())
+                page.locator("#confirmPassword").fill(u["password"].strip())
+                page.get_by_role("button", name="Sign Up").click()
+
+                # Let any redirect/JS complete before closing this page
+                page.wait_for_load_state("networkidle", timeout=7000)
+                print(f"✅ Signed up: {u['name']} ({u['email']})")
+            finally:
+                page.close()
+
+        browser.close()
+
+
+if __name__ == "__main__":
+    run_signup_from_csv("users.csv", headed=True)

requirements.txt

@@ -2,3 +2,6 @@ pytest>=8.0.0
 playwright>=1.45.0
 pytest-playwright>=0.5.0
 python-dotenv>=1.0.1
+pandas>=2.0.0
+numpy>=1.24.0
+SQLAlchemy>=2.0.0

tests/data_quality/test_data_anomalies.py

@@ -0,0 +1,14 @@
+import pytest
+from utils.data_validation.dataframe_utils import DataFrameValidator
+from data_clients.db_client import DatabaseClient
+
+def test_large_scale_data_stability(db_engine):
+    """
+    A skeleton test representing a data stability check.
+    It expects the 'db_engine' fixture from conftest.py.
+    """
+    # client = DatabaseClient(db_engine)
+    # df = client.get_system_snapshot("production_replica")
+    # validator = DataFrameValidator()
+    # validator.assert_no_anomalies(df)
+    pass

users.csv

@@ -0,0 +1,4 @@
+name,email,password
+Admin,[email protected],Pass123
+User,[email protected],Pass456
+Manager,[email protected],Pass789

utils/data_validation/dataframe_utils.py

@@ -0,0 +1,17 @@
+import pandas as pd
+import numpy as np
+
+class DataFrameValidator:
+    @staticmethod
+    def assert_no_anomalies(df: pd.DataFrame, threshold: float = 0.05):
+        """
+        Checks if the number of nulls exceeds a threshold.
+        """
+        pass
+
+    @staticmethod
+    def compare_snapshots(pre_df: pd.DataFrame, post_df: pd.DataFrame) -> pd.DataFrame:
+        """
+        Returns a diff between pre-code and post-code system states.
+        """
+        pass