Project: Words in both

Write a function called words_in_both that takes two strings and returns a set of the words that appear in both. You can assume every character is a letter or a space. Capitalization does not matter, so "to" and "To" are the same word. The words in the result set should be lower-case. For example, if one string has "on" and the other has "ON", the set should contain "on".

Python's split() method helps here:

sentence = 'Not the comfy chair!'
print(sentence.split())  # ['Not', 'the', 'comfy', 'chair!']

Here is how the function could be used:

common_words = words_in_both("She's a jack of all trades", 'Jack was tallest of all')

Save the file as words_in_both.py.

Show a solution

Try the project on your own first. This is one working solution, followed by its tests. Press Run to run the tests. Read them to see what thorough testing looks like, then change the solution and run again to watch a test fail.

def words_in_both(first: str, second: str) -> set:
    """Return the lower-case words that appear in both strings."""
    return set(first.lower().split()) & set(second.lower().split())

# ---- Tests ----
import sys
import unittest

class TestWordsInBoth(unittest.TestCase):
    def test_the_example_from_the_project_finds_three_shared_words(self):
        result = words_in_both("She's a jack of all trades", "Jack was tallest of all")
        self.assertEqual(result, {"jack", "of", "all"})

def test_a_word_in_only_one_string_is_left_out(self):
        self.assertEqual(words_in_both("red green blue", "green yellow"), {"green"})

def test_strings_with_no_words_in_common_give_an_empty_set(self):
        self.assertEqual(words_in_both("one two", "three four"), set())

def test_capitalization_does_not_matter(self):
        self.assertEqual(words_in_both("on", "ON"), {"on"})

def test_the_result_is_lower_case_whichever_string_had_capitals(self):
        self.assertEqual(words_in_both("To Be", "to be"), {"to", "be"})
        self.assertEqual(words_in_both("to be", "TO BE"), {"to", "be"})

def test_a_repeated_word_appears_once_in_the_set(self):
        self.assertEqual(words_in_both("go go go", "go"), {"go"})

def test_extra_spaces_do_not_create_empty_words(self):
        self.assertEqual(words_in_both("  a   b ", "b  a"), {"a", "b"})

def test_an_empty_string_has_no_words_in_common_with_anything(self):
        self.assertEqual(words_in_both("", "some words"), set())
        self.assertEqual(words_in_both("some words", ""), set())
        self.assertEqual(words_in_both("", ""), set())

def test_the_result_is_a_set(self):
        self.assertIsInstance(words_in_both("a", "a"), set)

# ---- Run the tests ----
loader = unittest.defaultTestLoader
suite = unittest.TestSuite(loader.loadTestsFromTestCase(case) for case in [TestWordsInBoth])
unittest.TextTestRunner(stream=sys.stdout, verbosity=2).run(suite)

I finished this project

Projects run on your own computer, so you tell us when you are done.