Debugging, Testing, Regular Expressions and Code Quality

def average(values):
    return sum(values) / len(values)
def report(data):
    return f"Average: {average(data['scores']):.1f}"
print(report({"scores": []}))

def average(values):
    return sum(values) / len(values) if values else None
print(average([]), average([4, 6]))

total = 0
for i, v in enumerate([5, 10, 15]):
    total += v
    print(f"{i=} {v=} {total=}")          # the = specifier prints the name and the value

def clean_city(raw):
    return " ".join(raw.split()).title() if raw else None

assert clean_city("  new   delhi ") == "New Delhi"
assert clean_city("") is None
print("asserts passed")

from pathlib import Path
import subprocess, sys
Path("tests_demo").mkdir(exist_ok=True)
Path("tests_demo/cleaning.py").write_text('''
def clean_city(raw):
    return " ".join(raw.split()).title() if raw else None

def to_inr(value):
    return f"₹{value:,.0f}"
''', encoding="utf-8")
Path("tests_demo/test_cleaning.py").write_text('''
import pytest
from cleaning import clean_city, to_inr

@pytest.mark.parametrize("raw, expected", [("  pune", "Pune"), ("NEW  DELHI", "New Delhi"), ("", None), (None, None)])
def test_clean_city(raw, expected):
    assert clean_city(raw) == expected

def test_to_inr():
    assert to_inr(1234567) == "₹1,234,567"

def test_bad_input():
    with pytest.raises(ValueError):          # a str cannot take the ',' number format
        to_inr("abc")

def test_deliberately_failing():
    assert to_inr(1000) == "₹1000"          # wrong expectation, to show a failure report
''', encoding="utf-8")
r = subprocess.run([sys.executable, "-m", "pytest", "-q", "--no-header", "-p", "no:cacheprovider", "tests_demo"], capture_output=True, text=True)
lines = r.stdout.strip().splitlines()
print("\n".join([l for l in lines if "assert" in l or "passed" in l or "failed" in l][-4:]))
import shutil; shutil.rmtree("tests_demo")

import re
text = "Call 98765-43210 or +91 91234 56789; email [email protected], [email protected]. Order #A-1029 on 2025-04-07."
print(re.findall(r"\d{5}[- ]?\d{5}", text))                              # phone numbers
print(re.findall(r"[\w.+-]+@[\w-]+(?:\.[\w-]+)+", text))                  # emails (no trailing full stop)
m = re.search(r"(?P<y>\d{4})-(?P<m>\d{2})-(?P<d>\d{2})", text)
print(m.group(), m["y"], m.groupdict())
print(re.sub(r"\d", "X", "PAN ABCDE1234F"), re.split(r"[;,]\s*", "a, b;c ,d"))
print(bool(re.fullmatch(r"[A-Z]{5}\d{4}[A-Z]", "ABCDE1234F")), bool(re.fullmatch(r"[A-Z]{5}\d{4}[A-Z]", "ABCD1234F")))    # PAN format

import pandas as pd
c = pd.DataFrame({"name": ["Asha", "Ravi", "Meera", "Kabir", "Zoya"],
                  "email": ["[email protected]", "ravi@company", "[email protected]", "kabir @gmail.com", None],
                  "phone": ["98765 43210", "+91-91234-56789", "12345", "9123456789", "0987654321"]})
c["email_ok"] = c["email"].str.fullmatch(r"[\w.+-]+@[\w-]+(?:\.[\w-]+)+", na=False)
c["domain"] = c["email"].str.lower().str.extract(r"@([\w.-]+)$")[0]
digits = c["phone"].str.replace(r"\D", "", regex=True).str[-10:]
c["phone_ok"] = digits.str.fullmatch(r"[6-9]\d{9}")
print(c[["name", "email_ok", "domain", "phone_ok"]])

pip install ruff mypy
ruff check .          # lint: unused imports, undefined names, bad patterns
ruff format .         # auto-format (black-compatible)
mypy src/             # check type hints
pre-commit install    # run them automatically before each commit